- 正直、最終結果は微妙です。。。
- が、せっかく試したので備忘録として残します
概要
日本語音声ファイルのテキスト化 + PII (個人情報) マスキング、ができないかという相談を受けたので AWS のサービスで検討を開始。
ぱっと思いついたのは Amazon Transcribe ですが、現時点 (2026/5月時点) で日本語の PII マスキング (リダクション) は不可。
PII マスキングは別のサービスで代替しないとということで候補に挙げたのが、Amazon Comprehend と AWS Glue DataBrew の 2 つ。
Comprehend の PII マスキング機能は、現時点 (2026/5月時点) で英語とスペイン語のみ。
Amazon Comprehend を使用して、英語またはスペイン語のテキストドキュメントで PII エンティティを検出できます。
ということで、PII マスキングについては Glue DataBrew で対応することにしました。
Glue DataBrew の日本語文字列に対する PII マスキング精度がいまいちということに気づく
そもそも自分のデータ整形が悪いと思うのですが、日本語文章から PII 文字列のマスキングがイマイチであることに途中で気づきました。
ということで、かなり力技ですが Amazon Translate で日本語文を一度英語文に翻訳し、その文をマスキングした後、再度 Translate で日本語に翻訳するという処理を追加しました。
構成
実際の構成は以下の通りです。
フローはざっくりと以下のとおりです。
- WAV ファイルを
Transcribeで文字起こし -
Transcribeから出力された JSON ファイルをLambdaで整形し、合わせて文章をTranslate SDKで英語に翻訳 -
DataBrewで PII マスキング - マスキング後のファイルを
Lambdaでテキストファイル化しつつ、合わせて文章をTranslate SDKで日本語に翻訳
- 環境コードは以下 GitHub にあげてますので、よかったら覗いてみてください
結果
音声ファイル
音声ファイルは Lambda で Amazon Polly SDK を呼び出して作成しました。
- 添付できないので省略させていただきます
Transcribe で文字起こししたファイル
実際に音声ファイルから文字起こしして出力されたファイルです。
文字起こし後JSONファイル
{
"jobName": "pii_include.wav-convert-job-670a842c-e68d-dd91-8e68-3807779697f4_a41f198a-82b2-d336-70ad-f92444922d9e",
"accountId": "123456789012",
"status": "COMPLETED",
"results": {
"transcripts": [
{
"transcript": "もしもし、お世話になっております。ヤマダタロウと申します。お電話ありがとうございます。防災サービス窓口の担当です。すみません、登録確認のメールを削除してしまいまして、再送が可能か確認したくてお電話しました。はい、承知しました。念のため、ご本人確認をさせてください。お名前はヤマダタロウさんでお間違いないでしょうか。はい、ヤマダタロウです。ありがとうございます。それでは、ご登録の電話番号をお願いいたします。はい。09012345678です。復唱いたします。09012345678ですね。続いて、メールアドレスをお願いいたします。ヤマダタロウアットエグザンプル.comです。ありがとうございます。では、内容を確認いたしますので、少々お待ちください。はい、お願いします。お待たせいたしました。確認メールは本日中に再送いたします。届かない場合は、迷惑メールフォルダもご確認ください。承知しました。ちなみに、再送は大体いつごろになりますか。目安にはなりますが、夕方ごろまでにはお届けできる見込みです。分かりました。ありがとうございます。よろしくお願いします。こちらこそ、よろしくお願いいたします。"
}
],
"speaker_labels": {
"segments": [
{
"start_time": "0.0",
"end_time": "5.4",
"speaker_label": "spk_0",
"items": [
{
"speaker_label": "spk_0",
"start_time": "0.07",
"end_time": "0.949"
},
{
"speaker_label": "spk_0",
"start_time": "1.279",
"end_time": "1.399"
},
{
"speaker_label": "spk_0",
"start_time": "1.399",
"end_time": "1.72"
},
{
"speaker_label": "spk_0",
"start_time": "1.72",
"end_time": "1.84"
},
{
"speaker_label": "spk_0",
"start_time": "1.84",
"end_time": "2.029"
},
{
"speaker_label": "spk_0",
"start_time": "2.029",
"end_time": "2.23"
},
{
"speaker_label": "spk_0",
"start_time": "2.23",
"end_time": "2.319"
},
{
"speaker_label": "spk_0",
"start_time": "2.319",
"end_time": "3.119"
},
{
"speaker_label": "spk_0",
"start_time": "3.24",
"end_time": "3.759"
},
{
"speaker_label": "spk_0",
"start_time": "3.759",
"end_time": "4.119"
},
{
"speaker_label": "spk_0",
"start_time": "4.119",
"end_time": "4.28"
},
{
"speaker_label": "spk_0",
"start_time": "4.28",
"end_time": "4.599"
},
{
"speaker_label": "spk_0",
"start_time": "4.599",
"end_time": "5.4"
}
]
},
{
"start_time": "5.55",
"end_time": "9.779",
"speaker_label": "spk_1",
"items": [
{
"speaker_label": "spk_1",
"start_time": "5.55",
"end_time": "5.67"
},
{
"speaker_label": "spk_1",
"start_time": "5.67",
"end_time": "6.039"
},
{
"speaker_label": "spk_1",
"start_time": "6.039",
"end_time": "6.659"
},
{
"speaker_label": "spk_1",
"start_time": "6.659",
"end_time": "6.88"
},
{
"speaker_label": "spk_1",
"start_time": "6.88",
"end_time": "7.449"
},
{
"speaker_label": "spk_1",
"start_time": "7.71",
"end_time": "8.229"
},
{
"speaker_label": "spk_1",
"start_time": "8.229",
"end_time": "8.64"
},
{
"speaker_label": "spk_1",
"start_time": "8.64",
"end_time": "9.109"
},
{
"speaker_label": "spk_1",
"start_time": "9.109",
"end_time": "9.229"
},
{
"speaker_label": "spk_1",
"start_time": "9.229",
"end_time": "9.779"
}
]
},
{
"start_time": "9.779",
"end_time": "18.879",
"speaker_label": "spk_0",
"items": [
{
"speaker_label": "spk_0",
"start_time": "9.779",
"end_time": "10.34"
},
{
"speaker_label": "spk_0",
"start_time": "10.71",
"end_time": "11.029"
},
{
"speaker_label": "spk_0",
"start_time": "11.029",
"end_time": "11.229"
},
{
"speaker_label": "spk_0",
"start_time": "11.229",
"end_time": "11.64"
},
{
"speaker_label": "spk_0",
"start_time": "11.989",
"end_time": "12.399"
},
{
"speaker_label": "spk_0",
"start_time": "12.399",
"end_time": "12.829"
},
{
"speaker_label": "spk_0",
"start_time": "12.829",
"end_time": "12.989"
},
{
"speaker_label": "spk_0",
"start_time": "12.989",
"end_time": "13.31"
},
{
"speaker_label": "spk_0",
"start_time": "13.31",
"end_time": "13.439"
},
{
"speaker_label": "spk_0",
"start_time": "13.439",
"end_time": "13.909"
},
{
"speaker_label": "spk_0",
"start_time": "13.909",
"end_time": "13.989"
},
{
"speaker_label": "spk_0",
"start_time": "13.989",
"end_time": "14.109"
},
{
"speaker_label": "spk_0",
"start_time": "14.109",
"end_time": "14.399"
},
{
"speaker_label": "spk_0",
"start_time": "14.399",
"end_time": "14.63"
},
{
"speaker_label": "spk_0",
"start_time": "14.63",
"end_time": "14.949"
},
{
"speaker_label": "spk_0",
"start_time": "15.43",
"end_time": "15.92"
},
{
"speaker_label": "spk_0",
"start_time": "15.92",
"end_time": "16.079"
},
{
"speaker_label": "spk_0",
"start_time": "16.079",
"end_time": "16.44"
},
{
"speaker_label": "spk_0",
"start_time": "16.44",
"end_time": "16.84"
},
{
"speaker_label": "spk_0",
"start_time": "16.84",
"end_time": "17.28"
},
{
"speaker_label": "spk_0",
"start_time": "17.28",
"end_time": "17.36"
},
{
"speaker_label": "spk_0",
"start_time": "17.36",
"end_time": "17.549"
},
{
"speaker_label": "spk_0",
"start_time": "17.549",
"end_time": "17.67"
},
{
"speaker_label": "spk_0",
"start_time": "17.67",
"end_time": "17.76"
},
{
"speaker_label": "spk_0",
"start_time": "17.76",
"end_time": "18.069"
},
{
"speaker_label": "spk_0",
"start_time": "18.069",
"end_time": "18.19"
},
{
"speaker_label": "spk_0",
"start_time": "18.19",
"end_time": "18.399"
},
{
"speaker_label": "spk_0",
"start_time": "18.399",
"end_time": "18.879"
}
]
},
{
"start_time": "19.159",
"end_time": "27.92",
"speaker_label": "spk_1",
"items": [
{
"speaker_label": "spk_1",
"start_time": "19.159",
"end_time": "19.52"
},
{
"speaker_label": "spk_1",
"start_time": "19.52",
"end_time": "19.94"
},
{
"speaker_label": "spk_1",
"start_time": "19.94",
"end_time": "20.059"
},
{
"speaker_label": "spk_1",
"start_time": "20.059",
"end_time": "20.28"
},
{
"speaker_label": "spk_1",
"start_time": "20.28",
"end_time": "20.76"
},
{
"speaker_label": "spk_1",
"start_time": "20.92",
"end_time": "21.19"
},
{
"speaker_label": "spk_1",
"start_time": "21.19",
"end_time": "21.34"
},
{
"speaker_label": "spk_1",
"start_time": "21.34",
"end_time": "21.799"
},
{
"speaker_label": "spk_1",
"start_time": "21.799",
"end_time": "21.959"
},
{
"speaker_label": "spk_1",
"start_time": "21.959",
"end_time": "22.36"
},
{
"speaker_label": "spk_1",
"start_time": "22.36",
"end_time": "22.829"
},
{
"speaker_label": "spk_1",
"start_time": "22.829",
"end_time": "22.95"
},
{
"speaker_label": "spk_1",
"start_time": "22.95",
"end_time": "23.049"
},
{
"speaker_label": "spk_1",
"start_time": "23.049",
"end_time": "23.229"
},
{
"speaker_label": "spk_1",
"start_time": "23.229",
"end_time": "23.569"
},
{
"speaker_label": "spk_1",
"start_time": "23.569",
"end_time": "24.079"
},
{
"speaker_label": "spk_1",
"start_time": "24.309",
"end_time": "24.44"
},
{
"speaker_label": "spk_1",
"start_time": "24.44",
"end_time": "24.829"
},
{
"speaker_label": "spk_1",
"start_time": "24.829",
"end_time": "25.12"
},
{
"speaker_label": "spk_1",
"start_time": "25.12",
"end_time": "25.559"
},
{
"speaker_label": "spk_1",
"start_time": "25.559",
"end_time": "25.92"
},
{
"speaker_label": "spk_1",
"start_time": "25.92",
"end_time": "26.079"
},
{
"speaker_label": "spk_1",
"start_time": "26.079",
"end_time": "26.229"
},
{
"speaker_label": "spk_1",
"start_time": "26.229",
"end_time": "26.319"
},
{
"speaker_label": "spk_1",
"start_time": "26.319",
"end_time": "26.829"
},
{
"speaker_label": "spk_1",
"start_time": "26.829",
"end_time": "27.19"
},
{
"speaker_label": "spk_1",
"start_time": "27.19",
"end_time": "27.389"
},
{
"speaker_label": "spk_1",
"start_time": "27.389",
"end_time": "27.92"
}
]
},
{
"start_time": "28.2",
"end_time": "29.909",
"speaker_label": "spk_0",
"items": [
{
"speaker_label": "spk_0",
"start_time": "28.2",
"end_time": "28.59"
},
{
"speaker_label": "spk_0",
"start_time": "28.639",
"end_time": "29.079"
},
{
"speaker_label": "spk_0",
"start_time": "29.079",
"end_time": "29.44"
},
{
"speaker_label": "spk_0",
"start_time": "29.44",
"end_time": "29.879"
}
]
},
{
"start_time": "30.219",
"end_time": "35.88",
"speaker_label": "spk_1",
"items": [
{
"speaker_label": "spk_1",
"start_time": "30.299",
"end_time": "30.979"
},
{
"speaker_label": "spk_1",
"start_time": "30.979",
"end_time": "31.219"
},
{
"speaker_label": "spk_1",
"start_time": "31.219",
"end_time": "31.94"
},
{
"speaker_label": "spk_1",
"start_time": "32.139",
"end_time": "32.34"
},
{
"speaker_label": "spk_1",
"start_time": "32.34",
"end_time": "32.49"
},
{
"speaker_label": "spk_1",
"start_time": "32.49",
"end_time": "32.77"
},
{
"speaker_label": "spk_1",
"start_time": "32.77",
"end_time": "32.939"
},
{
"speaker_label": "spk_1",
"start_time": "32.939",
"end_time": "33.33"
},
{
"speaker_label": "spk_1",
"start_time": "33.33",
"end_time": "33.49"
},
{
"speaker_label": "spk_1",
"start_time": "33.49",
"end_time": "33.849"
},
{
"speaker_label": "spk_1",
"start_time": "33.849",
"end_time": "34.279"
},
{
"speaker_label": "spk_1",
"start_time": "34.279",
"end_time": "34.58"
},
{
"speaker_label": "spk_1",
"start_time": "34.58",
"end_time": "34.819"
},
{
"speaker_label": "spk_1",
"start_time": "34.819",
"end_time": "35.049"
},
{
"speaker_label": "spk_1",
"start_time": "35.049",
"end_time": "35.279"
},
{
"speaker_label": "spk_1",
"start_time": "35.279",
"end_time": "35.88"
}
]
},
{
"start_time": "36.29",
"end_time": "40.099",
"speaker_label": "spk_0",
"items": [
{
"speaker_label": "spk_0",
"start_time": "36.29",
"end_time": "36.939"
},
{
"speaker_label": "spk_0",
"start_time": "37.09",
"end_time": "40.099"
}
]
},
{
"start_time": "40.099",
"end_time": "49.099",
"speaker_label": "spk_1",
"items": [
{
"speaker_label": "spk_1",
"start_time": "40.099",
"end_time": "40.68"
},
{
"speaker_label": "spk_1",
"start_time": "40.979",
"end_time": "41.54"
},
{
"speaker_label": "spk_1",
"start_time": "41.54",
"end_time": "41.86"
},
{
"speaker_label": "spk_1",
"start_time": "41.86",
"end_time": "42.369"
},
{
"speaker_label": "spk_1",
"start_time": "42.72",
"end_time": "45.65"
},
{
"speaker_label": "spk_1",
"start_time": "45.65",
"end_time": "45.81"
},
{
"speaker_label": "spk_1",
"start_time": "45.81",
"end_time": "46.34"
},
{
"speaker_label": "spk_1",
"start_time": "46.58",
"end_time": "46.97"
},
{
"speaker_label": "spk_1",
"start_time": "46.97",
"end_time": "47.319"
},
{
"speaker_label": "spk_1",
"start_time": "47.319",
"end_time": "47.619"
},
{
"speaker_label": "spk_1",
"start_time": "47.619",
"end_time": "48.169"
},
{
"speaker_label": "spk_1",
"start_time": "48.169",
"end_time": "48.419"
},
{
"speaker_label": "spk_1",
"start_time": "48.419",
"end_time": "48.619"
},
{
"speaker_label": "spk_1",
"start_time": "48.619",
"end_time": "48.86"
},
{
"speaker_label": "spk_1",
"start_time": "48.86",
"end_time": "49.099"
}
]
},
{
"start_time": "49.099",
"end_time": "54.38",
"speaker_label": "spk_0",
"items": [
{
"speaker_label": "spk_0",
"start_time": "49.099",
"end_time": "49.74"
},
{
"speaker_label": "spk_0",
"start_time": "50.06",
"end_time": "50.689"
},
{
"speaker_label": "spk_0",
"start_time": "51.049",
"end_time": "51.549"
},
{
"speaker_label": "spk_0",
"start_time": "51.549",
"end_time": "52.13"
},
{
"speaker_label": "spk_0",
"start_time": "52.25",
"end_time": "53.06"
},
{
"speaker_label": "spk_0",
"start_time": "53.409",
"end_time": "53.689"
},
{
"speaker_label": "spk_0",
"start_time": "53.689",
"end_time": "54.38"
}
]
},
{
"start_time": "54.58",
"end_time": "60.009",
"speaker_label": "spk_1",
"items": [
{
"speaker_label": "spk_1",
"start_time": "54.58",
"end_time": "55.2"
},
{
"speaker_label": "spk_1",
"start_time": "55.2",
"end_time": "55.419"
},
{
"speaker_label": "spk_1",
"start_time": "55.419",
"end_time": "56.099"
},
{
"speaker_label": "spk_1",
"start_time": "56.29",
"end_time": "56.45"
},
{
"speaker_label": "spk_1",
"start_time": "56.45",
"end_time": "56.77"
},
{
"speaker_label": "spk_1",
"start_time": "56.77",
"end_time": "57.209"
},
{
"speaker_label": "spk_1",
"start_time": "57.209",
"end_time": "57.33"
},
{
"speaker_label": "spk_1",
"start_time": "57.33",
"end_time": "57.86"
},
{
"speaker_label": "spk_1",
"start_time": "57.86",
"end_time": "58.049"
},
{
"speaker_label": "spk_1",
"start_time": "58.049",
"end_time": "58.25"
},
{
"speaker_label": "spk_1",
"start_time": "58.25",
"end_time": "58.38"
},
{
"speaker_label": "spk_1",
"start_time": "58.38",
"end_time": "58.779"
},
{
"speaker_label": "spk_1",
"start_time": "58.779",
"end_time": "59.18"
},
{
"speaker_label": "spk_1",
"start_time": "59.18",
"end_time": "59.2"
},
{
"speaker_label": "spk_1",
"start_time": "59.2",
"end_time": "59.74"
},
{
"speaker_label": "spk_1",
"start_time": "59.74",
"end_time": "59.979"
}
]
},
{
"start_time": "60.439",
"end_time": "62.31",
"speaker_label": "spk_0",
"items": [
{
"speaker_label": "spk_0",
"start_time": "60.509",
"end_time": "61.08"
},
{
"speaker_label": "spk_0",
"start_time": "61.08",
"end_time": "61.31"
},
{
"speaker_label": "spk_0",
"start_time": "61.31",
"end_time": "61.56"
},
{
"speaker_label": "spk_0",
"start_time": "61.56",
"end_time": "61.669"
},
{
"speaker_label": "spk_0",
"start_time": "61.669",
"end_time": "62.31"
}
]
},
{
"start_time": "62.569",
"end_time": "72.04",
"speaker_label": "spk_1",
"items": [
{
"speaker_label": "spk_1",
"start_time": "62.569",
"end_time": "62.669"
},
{
"speaker_label": "spk_1",
"start_time": "62.669",
"end_time": "62.99"
},
{
"speaker_label": "spk_1",
"start_time": "62.99",
"end_time": "63.15"
},
{
"speaker_label": "spk_1",
"start_time": "63.15",
"end_time": "63.43"
},
{
"speaker_label": "spk_1",
"start_time": "63.43",
"end_time": "63.65"
},
{
"speaker_label": "spk_1",
"start_time": "63.65",
"end_time": "64.199"
},
{
"speaker_label": "spk_1",
"start_time": "64.389",
"end_time": "64.87"
},
{
"speaker_label": "spk_1",
"start_time": "64.87",
"end_time": "65.19"
},
{
"speaker_label": "spk_1",
"start_time": "65.19",
"end_time": "65.5"
},
{
"speaker_label": "spk_1",
"start_time": "65.5",
"end_time": "66.0"
},
{
"speaker_label": "spk_1",
"start_time": "66.0",
"end_time": "66.23"
},
{
"speaker_label": "spk_1",
"start_time": "66.23",
"end_time": "66.4"
},
{
"speaker_label": "spk_1",
"start_time": "66.4",
"end_time": "66.919"
},
{
"speaker_label": "spk_1",
"start_time": "66.919",
"end_time": "67.12"
},
{
"speaker_label": "spk_1",
"start_time": "67.12",
"end_time": "67.709"
},
{
"speaker_label": "spk_1",
"start_time": "67.959",
"end_time": "68.239"
},
{
"speaker_label": "spk_1",
"start_time": "68.239",
"end_time": "68.389"
},
{
"speaker_label": "spk_1",
"start_time": "68.389",
"end_time": "68.599"
},
{
"speaker_label": "spk_1",
"start_time": "68.599",
"end_time": "68.94"
},
{
"speaker_label": "spk_1",
"start_time": "68.94",
"end_time": "69.239"
},
{
"speaker_label": "spk_1",
"start_time": "69.239",
"end_time": "69.83"
},
{
"speaker_label": "spk_1",
"start_time": "69.83",
"end_time": "70.15"
},
{
"speaker_label": "spk_1",
"start_time": "70.15",
"end_time": "70.559"
},
{
"speaker_label": "spk_1",
"start_time": "70.559",
"end_time": "70.68"
},
{
"speaker_label": "spk_1",
"start_time": "70.68",
"end_time": "70.83"
},
{
"speaker_label": "spk_1",
"start_time": "70.83",
"end_time": "71.519"
},
{
"speaker_label": "spk_1",
"start_time": "71.519",
"end_time": "72.04"
}
]
},
{
"start_time": "72.4",
"end_time": "77.199",
"speaker_label": "spk_0",
"items": [
{
"speaker_label": "spk_0",
"start_time": "72.4",
"end_time": "72.819"
},
{
"speaker_label": "spk_0",
"start_time": "72.819",
"end_time": "72.9"
},
{
"speaker_label": "spk_0",
"start_time": "72.9",
"end_time": "73.15"
},
{
"speaker_label": "spk_0",
"start_time": "73.15",
"end_time": "73.599"
},
{
"speaker_label": "spk_0",
"start_time": "73.839",
"end_time": "74.279"
},
{
"speaker_label": "spk_0",
"start_time": "74.279",
"end_time": "74.599"
},
{
"speaker_label": "spk_0",
"start_time": "74.75",
"end_time": "75.199"
},
{
"speaker_label": "spk_0",
"start_time": "75.199",
"end_time": "75.339"
},
{
"speaker_label": "spk_0",
"start_time": "75.339",
"end_time": "75.72"
},
{
"speaker_label": "spk_0",
"start_time": "75.72",
"end_time": "76.199"
},
{
"speaker_label": "spk_0",
"start_time": "76.199",
"end_time": "76.309"
},
{
"speaker_label": "spk_0",
"start_time": "76.309",
"end_time": "76.48"
},
{
"speaker_label": "spk_0",
"start_time": "76.48",
"end_time": "76.68"
},
{
"speaker_label": "spk_0",
"start_time": "76.68",
"end_time": "77.199"
}
]
},
{
"start_time": "77.44",
"end_time": "81.44",
"speaker_label": "spk_1",
"items": [
{
"speaker_label": "spk_1",
"start_time": "77.44",
"end_time": "77.83"
},
{
"speaker_label": "spk_1",
"start_time": "77.83",
"end_time": "77.959"
},
{
"speaker_label": "spk_1",
"start_time": "77.959",
"end_time": "78.11"
},
{
"speaker_label": "spk_1",
"start_time": "78.11",
"end_time": "78.279"
},
{
"speaker_label": "spk_1",
"start_time": "78.279",
"end_time": "78.55"
},
{
"speaker_label": "spk_1",
"start_time": "78.55",
"end_time": "78.849"
},
{
"speaker_label": "spk_1",
"start_time": "78.849",
"end_time": "79.389"
},
{
"speaker_label": "spk_1",
"start_time": "79.389",
"end_time": "79.65"
},
{
"speaker_label": "spk_1",
"start_time": "79.65",
"end_time": "79.8"
},
{
"speaker_label": "spk_1",
"start_time": "79.8",
"end_time": "79.919"
},
{
"speaker_label": "spk_1",
"start_time": "79.919",
"end_time": "80.04"
},
{
"speaker_label": "spk_1",
"start_time": "80.04",
"end_time": "80.199"
},
{
"speaker_label": "spk_1",
"start_time": "80.199",
"end_time": "80.269"
},
{
"speaker_label": "spk_1",
"start_time": "80.269",
"end_time": "80.629"
},
{
"speaker_label": "spk_1",
"start_time": "80.629",
"end_time": "81.01"
},
{
"speaker_label": "spk_1",
"start_time": "81.01",
"end_time": "81.44"
}
]
},
{
"start_time": "81.44",
"end_time": "86.389",
"speaker_label": "spk_0",
"items": [
{
"speaker_label": "spk_0",
"start_time": "81.44",
"end_time": "82.199"
},
{
"speaker_label": "spk_0",
"start_time": "82.51",
"end_time": "82.669"
},
{
"speaker_label": "spk_0",
"start_time": "82.669",
"end_time": "82.91"
},
{
"speaker_label": "spk_0",
"start_time": "82.91",
"end_time": "83.36"
},
{
"speaker_label": "spk_0",
"start_time": "83.589",
"end_time": "84.199"
},
{
"speaker_label": "spk_0",
"start_time": "84.199",
"end_time": "84.4"
},
{
"speaker_label": "spk_0",
"start_time": "84.4",
"end_time": "85.0"
},
{
"speaker_label": "spk_0",
"start_time": "85.279",
"end_time": "85.79"
},
{
"speaker_label": "spk_0",
"start_time": "85.79",
"end_time": "86.029"
},
{
"speaker_label": "spk_0",
"start_time": "86.029",
"end_time": "86.25"
},
{
"speaker_label": "spk_0",
"start_time": "86.25",
"end_time": "86.389"
}
]
},
{
"start_time": "86.389",
"end_time": "89.699",
"speaker_label": "spk_1",
"items": [
{
"speaker_label": "spk_1",
"start_time": "86.389",
"end_time": "87.04"
},
{
"speaker_label": "spk_1",
"start_time": "87.309",
"end_time": "87.699"
},
{
"speaker_label": "spk_1",
"start_time": "87.699",
"end_time": "88.11"
},
{
"speaker_label": "spk_1",
"start_time": "88.11",
"end_time": "88.599"
},
{
"speaker_label": "spk_1",
"start_time": "88.599",
"end_time": "88.839"
},
{
"speaker_label": "spk_1",
"start_time": "88.839",
"end_time": "89.08"
},
{
"speaker_label": "spk_1",
"start_time": "89.08",
"end_time": "89.319"
},
{
"speaker_label": "spk_1",
"start_time": "89.319",
"end_time": "89.669"
}
]
}
],
"channel_label": "ch_0",
"speakers": 2
},
"items": [
{
"id": 0,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.758", "content": "もしもし、" }],
"start_time": "0.07",
"end_time": "0.949",
"speaker_label": "spk_0"
},
{
"id": 1,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "お" }],
"start_time": "1.279",
"end_time": "1.399",
"speaker_label": "spk_0"
},
{
"id": 2,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.997", "content": "世話" }],
"start_time": "1.399",
"end_time": "1.72",
"speaker_label": "spk_0"
},
{
"id": 3,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "に" }],
"start_time": "1.72",
"end_time": "1.84",
"speaker_label": "spk_0"
},
{
"id": 4,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "なっ" }],
"start_time": "1.84",
"end_time": "2.029",
"speaker_label": "spk_0"
},
{
"id": 5,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "て" }],
"start_time": "2.029",
"end_time": "2.23",
"speaker_label": "spk_0"
},
{
"id": 6,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "おり" }],
"start_time": "2.23",
"end_time": "2.319",
"speaker_label": "spk_0"
},
{
"id": 7,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.963", "content": "ます。" }],
"start_time": "2.319",
"end_time": "3.119",
"speaker_label": "spk_0"
},
{
"id": 8,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.757", "content": "ヤマダ" }],
"start_time": "3.24",
"end_time": "3.759",
"speaker_label": "spk_0"
},
{
"id": 9,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.817", "content": "タロウ" }],
"start_time": "3.759",
"end_time": "4.119",
"speaker_label": "spk_0"
},
{
"id": 10,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "と" }],
"start_time": "4.119",
"end_time": "4.28",
"speaker_label": "spk_0"
},
{
"id": 11,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "申し" }],
"start_time": "4.28",
"end_time": "4.599",
"speaker_label": "spk_0"
},
{
"id": 12,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.993", "content": "ます。" }],
"start_time": "4.599",
"end_time": "5.4",
"speaker_label": "spk_0"
},
{
"id": 13,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "お" }],
"start_time": "5.55",
"end_time": "5.67",
"speaker_label": "spk_1"
},
{
"id": 14,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "電話" }],
"start_time": "5.67",
"end_time": "6.039",
"speaker_label": "spk_1"
},
{
"id": 15,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "ありがとう" }],
"start_time": "6.039",
"end_time": "6.659",
"speaker_label": "spk_1"
},
{
"id": 16,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.997", "content": "ござい" }],
"start_time": "6.659",
"end_time": "6.88",
"speaker_label": "spk_1"
},
{
"id": 17,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.99", "content": "ます。" }],
"start_time": "6.88",
"end_time": "7.449",
"speaker_label": "spk_1"
},
{
"id": 18,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "防災" }],
"start_time": "7.71",
"end_time": "8.229",
"speaker_label": "spk_1"
},
{
"id": 19,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "サービス" }],
"start_time": "8.229",
"end_time": "8.64",
"speaker_label": "spk_1"
},
{
"id": 20,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.997", "content": "窓口" }],
"start_time": "8.64",
"end_time": "9.109",
"speaker_label": "spk_1"
},
{
"id": 21,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "の" }],
"start_time": "9.109",
"end_time": "9.229",
"speaker_label": "spk_1"
},
{
"id": 22,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.997", "content": "担当" }],
"start_time": "9.229",
"end_time": "9.779",
"speaker_label": "spk_1"
},
{
"id": 23,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.988", "content": "です。" }],
"start_time": "9.779",
"end_time": "10.34",
"speaker_label": "spk_0"
},
{
"id": 24,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.996", "content": "すみ" }],
"start_time": "10.71",
"end_time": "11.029",
"speaker_label": "spk_0"
},
{
"id": 25,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "ませ" }],
"start_time": "11.029",
"end_time": "11.229",
"speaker_label": "spk_0"
},
{
"id": 26,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.491", "content": "ん、" }],
"start_time": "11.229",
"end_time": "11.64",
"speaker_label": "spk_0"
},
{
"id": 27,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "登録" }],
"start_time": "11.989",
"end_time": "12.399",
"speaker_label": "spk_0"
},
{
"id": 28,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "確認" }],
"start_time": "12.399",
"end_time": "12.829",
"speaker_label": "spk_0"
},
{
"id": 29,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "の" }],
"start_time": "12.829",
"end_time": "12.989",
"speaker_label": "spk_0"
},
{
"id": 30,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "メール" }],
"start_time": "12.989",
"end_time": "13.31",
"speaker_label": "spk_0"
},
{
"id": 31,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "を" }],
"start_time": "13.31",
"end_time": "13.439",
"speaker_label": "spk_0"
},
{
"id": 32,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.995", "content": "削除" }],
"start_time": "13.439",
"end_time": "13.909",
"speaker_label": "spk_0"
},
{
"id": 33,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "し" }],
"start_time": "13.909",
"end_time": "13.989",
"speaker_label": "spk_0"
},
{
"id": 34,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "て" }],
"start_time": "13.989",
"end_time": "14.109",
"speaker_label": "spk_0"
},
{
"id": 35,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.997", "content": "しまい" }],
"start_time": "14.109",
"end_time": "14.399",
"speaker_label": "spk_0"
},
{
"id": 36,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "まし" }],
"start_time": "14.399",
"end_time": "14.63",
"speaker_label": "spk_0"
},
{
"id": 37,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.851", "content": "て、" }],
"start_time": "14.63",
"end_time": "14.949",
"speaker_label": "spk_0"
},
{
"id": 38,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.989", "content": "再送" }],
"start_time": "15.43",
"end_time": "15.92",
"speaker_label": "spk_0"
},
{
"id": 39,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "が" }],
"start_time": "15.92",
"end_time": "16.079",
"speaker_label": "spk_0"
},
{
"id": 40,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "可能" }],
"start_time": "16.079",
"end_time": "16.44",
"speaker_label": "spk_0"
},
{
"id": 41,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "か" }],
"start_time": "16.44",
"end_time": "16.84",
"speaker_label": "spk_0"
},
{
"id": 42,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "確認" }],
"start_time": "16.84",
"end_time": "17.28",
"speaker_label": "spk_0"
},
{
"id": 43,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "し" }],
"start_time": "17.28",
"end_time": "17.36",
"speaker_label": "spk_0"
},
{
"id": 44,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "たく" }],
"start_time": "17.36",
"end_time": "17.549",
"speaker_label": "spk_0"
},
{
"id": 45,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "て" }],
"start_time": "17.549",
"end_time": "17.67",
"speaker_label": "spk_0"
},
{
"id": 46,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "お" }],
"start_time": "17.67",
"end_time": "17.76",
"speaker_label": "spk_0"
},
{
"id": 47,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "電話" }],
"start_time": "17.76",
"end_time": "18.069",
"speaker_label": "spk_0"
},
{
"id": 48,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.998", "content": "し" }],
"start_time": "18.069",
"end_time": "18.19",
"speaker_label": "spk_0"
},
{
"id": 49,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "まし" }],
"start_time": "18.19",
"end_time": "18.399",
"speaker_label": "spk_0"
},
{
"id": 50,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.993", "content": "た。" }],
"start_time": "18.399",
"end_time": "18.879",
"speaker_label": "spk_0"
},
{
"id": 51,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.901", "content": "はい、" }],
"start_time": "19.159",
"end_time": "19.52",
"speaker_label": "spk_1"
},
{
"id": 52,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.997", "content": "承知" }],
"start_time": "19.52",
"end_time": "19.94",
"speaker_label": "spk_1"
},
{
"id": 53,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "し" }],
"start_time": "19.94",
"end_time": "20.059",
"speaker_label": "spk_1"
},
{
"id": 54,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "まし" }],
"start_time": "20.059",
"end_time": "20.28",
"speaker_label": "spk_1"
},
{
"id": 55,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.99", "content": "た。" }],
"start_time": "20.28",
"end_time": "20.76",
"speaker_label": "spk_1"
},
{
"id": 56,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.995", "content": "念" }],
"start_time": "20.92",
"end_time": "21.19",
"speaker_label": "spk_1"
},
{
"id": 57,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "の" }],
"start_time": "21.19",
"end_time": "21.34",
"speaker_label": "spk_1"
},
{
"id": 58,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.795", "content": "ため、" }],
"start_time": "21.34",
"end_time": "21.799",
"speaker_label": "spk_1"
},
{
"id": 59,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.998", "content": "ご" }],
"start_time": "21.799",
"end_time": "21.959",
"speaker_label": "spk_1"
},
{
"id": 60,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "本人" }],
"start_time": "21.959",
"end_time": "22.36",
"speaker_label": "spk_1"
},
{
"id": 61,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "確認" }],
"start_time": "22.36",
"end_time": "22.829",
"speaker_label": "spk_1"
},
{
"id": 62,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.989", "content": "を" }],
"start_time": "22.829",
"end_time": "22.95",
"speaker_label": "spk_1"
},
{
"id": 63,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "さ" }],
"start_time": "22.95",
"end_time": "23.049",
"speaker_label": "spk_1"
},
{
"id": 64,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "せ" }],
"start_time": "23.049",
"end_time": "23.229",
"speaker_label": "spk_1"
},
{
"id": 65,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "て" }],
"start_time": "23.229",
"end_time": "23.569",
"speaker_label": "spk_1"
},
{
"id": 66,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.987", "content": "ください。" }],
"start_time": "23.569",
"end_time": "24.079",
"speaker_label": "spk_1"
},
{
"id": 67,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "お" }],
"start_time": "24.309",
"end_time": "24.44",
"speaker_label": "spk_1"
},
{
"id": 68,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "名前" }],
"start_time": "24.44",
"end_time": "24.829",
"speaker_label": "spk_1"
},
{
"id": 69,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "は" }],
"start_time": "24.829",
"end_time": "25.12",
"speaker_label": "spk_1"
},
{
"id": 70,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.777", "content": "ヤマダ" }],
"start_time": "25.12",
"end_time": "25.559",
"speaker_label": "spk_1"
},
{
"id": 71,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.846", "content": "タロウ" }],
"start_time": "25.559",
"end_time": "25.92",
"speaker_label": "spk_1"
},
{
"id": 72,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.998", "content": "さん" }],
"start_time": "25.92",
"end_time": "26.079",
"speaker_label": "spk_1"
},
{
"id": 73,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "で" }],
"start_time": "26.079",
"end_time": "26.229",
"speaker_label": "spk_1"
},
{
"id": 74,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "お" }],
"start_time": "26.229",
"end_time": "26.319",
"speaker_label": "spk_1"
},
{
"id": 75,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.974", "content": "間違い" }],
"start_time": "26.319",
"end_time": "26.829",
"speaker_label": "spk_1"
},
{
"id": 76,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.998", "content": "ない" }],
"start_time": "26.829",
"end_time": "27.19",
"speaker_label": "spk_1"
},
{
"id": 77,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "でしょう" }],
"start_time": "27.19",
"end_time": "27.389",
"speaker_label": "spk_1"
},
{
"id": 78,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.956", "content": "か。" }],
"start_time": "27.389",
"end_time": "27.92",
"speaker_label": "spk_1"
},
{
"id": 79,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.809", "content": "はい、" }],
"start_time": "28.2",
"end_time": "28.59",
"speaker_label": "spk_0"
},
{
"id": 80,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.766", "content": "ヤマダ" }],
"start_time": "28.639",
"end_time": "29.079",
"speaker_label": "spk_0"
},
{
"id": 81,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.828", "content": "タロウ" }],
"start_time": "29.079",
"end_time": "29.44",
"speaker_label": "spk_0"
},
{
"id": 82,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.977", "content": "です。" }],
"start_time": "29.44",
"end_time": "29.879",
"speaker_label": "spk_0"
},
{
"id": 83,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "ありがとう" }],
"start_time": "30.299",
"end_time": "30.979",
"speaker_label": "spk_1"
},
{
"id": 84,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "ござい" }],
"start_time": "30.979",
"end_time": "31.219",
"speaker_label": "spk_1"
},
{
"id": 85,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.996", "content": "ます。" }],
"start_time": "31.219",
"end_time": "31.94",
"speaker_label": "spk_1"
},
{
"id": 86,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "それ" }],
"start_time": "32.139",
"end_time": "32.34",
"speaker_label": "spk_1"
},
{
"id": 87,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "で" }],
"start_time": "32.34",
"end_time": "32.49",
"speaker_label": "spk_1"
},
{
"id": 88,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.776", "content": "は、" }],
"start_time": "32.49",
"end_time": "32.77",
"speaker_label": "spk_1"
},
{
"id": 89,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "ご" }],
"start_time": "32.77",
"end_time": "32.939",
"speaker_label": "spk_1"
},
{
"id": 90,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "登録" }],
"start_time": "32.939",
"end_time": "33.33",
"speaker_label": "spk_1"
},
{
"id": 91,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "の" }],
"start_time": "33.33",
"end_time": "33.49",
"speaker_label": "spk_1"
},
{
"id": 92,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "電話" }],
"start_time": "33.49",
"end_time": "33.849",
"speaker_label": "spk_1"
},
{
"id": 93,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "番号" }],
"start_time": "33.849",
"end_time": "34.279",
"speaker_label": "spk_1"
},
{
"id": 94,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.997", "content": "を" }],
"start_time": "34.279",
"end_time": "34.58",
"speaker_label": "spk_1"
},
{
"id": 95,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "お" }],
"start_time": "34.58",
"end_time": "34.819",
"speaker_label": "spk_1"
},
{
"id": 96,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "願い" }],
"start_time": "34.819",
"end_time": "35.049",
"speaker_label": "spk_1"
},
{
"id": 97,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.985", "content": "いたし" }],
"start_time": "35.049",
"end_time": "35.279",
"speaker_label": "spk_1"
},
{
"id": 98,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.995", "content": "ます。" }],
"start_time": "35.279",
"end_time": "35.88",
"speaker_label": "spk_1"
},
{
"id": 99,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.819", "content": "はい。" }],
"start_time": "36.29",
"end_time": "36.939",
"speaker_label": "spk_0"
},
{
"id": 100,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.204", "content": "09012345678" }],
"start_time": "37.09",
"end_time": "40.099",
"speaker_label": "spk_0"
},
{
"id": 101,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.996", "content": "です。" }],
"start_time": "40.099",
"end_time": "40.68",
"speaker_label": "spk_1"
},
{
"id": 102,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "復唱" }],
"start_time": "40.979",
"end_time": "41.54",
"speaker_label": "spk_1"
},
{
"id": 103,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.986", "content": "いたし" }],
"start_time": "41.54",
"end_time": "41.86",
"speaker_label": "spk_1"
},
{
"id": 104,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.988", "content": "ます。" }],
"start_time": "41.86",
"end_time": "42.369",
"speaker_label": "spk_1"
},
{
"id": 105,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.284", "content": "09012345678" }],
"start_time": "42.72",
"end_time": "45.65",
"speaker_label": "spk_1"
},
{
"id": 106,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "です" }],
"start_time": "45.65",
"end_time": "45.81",
"speaker_label": "spk_1"
},
{
"id": 107,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.991", "content": "ね。" }],
"start_time": "45.81",
"end_time": "46.34",
"speaker_label": "spk_1"
},
{
"id": 108,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.993", "content": "続い" }],
"start_time": "46.58",
"end_time": "46.97",
"speaker_label": "spk_1"
},
{
"id": 109,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.687", "content": "て、" }],
"start_time": "46.97",
"end_time": "47.319",
"speaker_label": "spk_1"
},
{
"id": 110,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "メール" }],
"start_time": "47.319",
"end_time": "47.619",
"speaker_label": "spk_1"
},
{
"id": 111,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "アドレス" }],
"start_time": "47.619",
"end_time": "48.169",
"speaker_label": "spk_1"
},
{
"id": 112,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "を" }],
"start_time": "48.169",
"end_time": "48.419",
"speaker_label": "spk_1"
},
{
"id": 113,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "お" }],
"start_time": "48.419",
"end_time": "48.619",
"speaker_label": "spk_1"
},
{
"id": 114,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "願い" }],
"start_time": "48.619",
"end_time": "48.86",
"speaker_label": "spk_1"
},
{
"id": 115,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.984", "content": "いたし" }],
"start_time": "48.86",
"end_time": "49.099",
"speaker_label": "spk_1"
},
{
"id": 116,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.995", "content": "ます。" }],
"start_time": "49.099",
"end_time": "49.74",
"speaker_label": "spk_0"
},
{
"id": 117,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.772", "content": "ヤマダ" }],
"start_time": "50.06",
"end_time": "50.689",
"speaker_label": "spk_0"
},
{
"id": 118,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.817", "content": "タロウ" }],
"start_time": "51.049",
"end_time": "51.549",
"speaker_label": "spk_0"
},
{
"id": 119,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.877", "content": "アット" }],
"start_time": "51.549",
"end_time": "52.13",
"speaker_label": "spk_0"
},
{
"id": 120,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.897", "content": "エグザンプル" }],
"start_time": "52.25",
"end_time": "53.06",
"speaker_label": "spk_0"
},
{
"id": 121,
"type": "punctuation",
"alternatives": [{ "confidence": "0.0", "content": "." }],
"speaker_label": "spk_0"
},
{
"id": 122,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.825", "content": "com" }],
"start_time": "53.409",
"end_time": "53.689",
"speaker_label": "spk_0"
},
{
"id": 123,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.993", "content": "です。" }],
"start_time": "53.689",
"end_time": "54.38",
"speaker_label": "spk_0"
},
{
"id": 124,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "ありがとう" }],
"start_time": "54.58",
"end_time": "55.2",
"speaker_label": "spk_1"
},
{
"id": 125,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "ござい" }],
"start_time": "55.2",
"end_time": "55.419",
"speaker_label": "spk_1"
},
{
"id": 126,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.993", "content": "ます。" }],
"start_time": "55.419",
"end_time": "56.099",
"speaker_label": "spk_1"
},
{
"id": 127,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "で" }],
"start_time": "56.29",
"end_time": "56.45",
"speaker_label": "spk_1"
},
{
"id": 128,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.871", "content": "は、" }],
"start_time": "56.45",
"end_time": "56.77",
"speaker_label": "spk_1"
},
{
"id": 129,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "内容" }],
"start_time": "56.77",
"end_time": "57.209",
"speaker_label": "spk_1"
},
{
"id": 130,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "を" }],
"start_time": "57.209",
"end_time": "57.33",
"speaker_label": "spk_1"
},
{
"id": 131,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "確認" }],
"start_time": "57.33",
"end_time": "57.86",
"speaker_label": "spk_1"
},
{
"id": 132,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.984", "content": "いたし" }],
"start_time": "57.86",
"end_time": "58.049",
"speaker_label": "spk_1"
},
{
"id": 133,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "ます" }],
"start_time": "58.049",
"end_time": "58.25",
"speaker_label": "spk_1"
},
{
"id": 134,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "の" }],
"start_time": "58.25",
"end_time": "58.38",
"speaker_label": "spk_1"
},
{
"id": 135,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.89", "content": "で、" }],
"start_time": "58.38",
"end_time": "58.779",
"speaker_label": "spk_1"
},
{
"id": 136,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "少々" }],
"start_time": "58.779",
"end_time": "59.18",
"speaker_label": "spk_1"
},
{
"id": 137,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "お" }],
"start_time": "59.18",
"end_time": "59.2",
"speaker_label": "spk_1"
},
{
"id": 138,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.997", "content": "待ち" }],
"start_time": "59.2",
"end_time": "59.74",
"speaker_label": "spk_1"
},
{
"id": 139,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.988", "content": "ください。" }],
"start_time": "59.74",
"end_time": "59.979",
"speaker_label": "spk_1"
},
{
"id": 140,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.847", "content": "はい、" }],
"start_time": "60.509",
"end_time": "61.08",
"speaker_label": "spk_0"
},
{
"id": 141,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "お" }],
"start_time": "61.08",
"end_time": "61.31",
"speaker_label": "spk_0"
},
{
"id": 142,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "願い" }],
"start_time": "61.31",
"end_time": "61.56",
"speaker_label": "spk_0"
},
{
"id": 143,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "し" }],
"start_time": "61.56",
"end_time": "61.669",
"speaker_label": "spk_0"
},
{
"id": 144,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.99", "content": "ます。" }],
"start_time": "61.669",
"end_time": "62.31",
"speaker_label": "spk_0"
},
{
"id": 145,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "お" }],
"start_time": "62.569",
"end_time": "62.669",
"speaker_label": "spk_1"
},
{
"id": 146,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.998", "content": "待た" }],
"start_time": "62.669",
"end_time": "62.99",
"speaker_label": "spk_1"
},
{
"id": 147,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "せ" }],
"start_time": "62.99",
"end_time": "63.15",
"speaker_label": "spk_1"
},
{
"id": 148,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.988", "content": "いたし" }],
"start_time": "63.15",
"end_time": "63.43",
"speaker_label": "spk_1"
},
{
"id": 149,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "まし" }],
"start_time": "63.43",
"end_time": "63.65",
"speaker_label": "spk_1"
},
{
"id": 150,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.991", "content": "た。" }],
"start_time": "63.65",
"end_time": "64.199",
"speaker_label": "spk_1"
},
{
"id": 151,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "確認" }],
"start_time": "64.389",
"end_time": "64.87",
"speaker_label": "spk_1"
},
{
"id": 152,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "メール" }],
"start_time": "64.87",
"end_time": "65.19",
"speaker_label": "spk_1"
},
{
"id": 153,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "は" }],
"start_time": "65.19",
"end_time": "65.5",
"speaker_label": "spk_1"
},
{
"id": 154,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "本日" }],
"start_time": "65.5",
"end_time": "66.0",
"speaker_label": "spk_1"
},
{
"id": 155,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "中" }],
"start_time": "66.0",
"end_time": "66.23",
"speaker_label": "spk_1"
},
{
"id": 156,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "に" }],
"start_time": "66.23",
"end_time": "66.4",
"speaker_label": "spk_1"
},
{
"id": 157,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.986", "content": "再送" }],
"start_time": "66.4",
"end_time": "66.919",
"speaker_label": "spk_1"
},
{
"id": 158,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.985", "content": "いたし" }],
"start_time": "66.919",
"end_time": "67.12",
"speaker_label": "spk_1"
},
{
"id": 159,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.995", "content": "ます。" }],
"start_time": "67.12",
"end_time": "67.709",
"speaker_label": "spk_1"
},
{
"id": 160,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "届" }],
"start_time": "67.959",
"end_time": "68.239",
"speaker_label": "spk_1"
},
{
"id": 161,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.986", "content": "か" }],
"start_time": "68.239",
"end_time": "68.389",
"speaker_label": "spk_1"
},
{
"id": 162,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "ない" }],
"start_time": "68.389",
"end_time": "68.599",
"speaker_label": "spk_1"
},
{
"id": 163,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "場合" }],
"start_time": "68.599",
"end_time": "68.94",
"speaker_label": "spk_1"
},
{
"id": 164,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.73", "content": "は、" }],
"start_time": "68.94",
"end_time": "69.239",
"speaker_label": "spk_1"
},
{
"id": 165,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "迷惑" }],
"start_time": "69.239",
"end_time": "69.83",
"speaker_label": "spk_1"
},
{
"id": 166,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "メール" }],
"start_time": "69.83",
"end_time": "70.15",
"speaker_label": "spk_1"
},
{
"id": 167,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.916", "content": "フォルダ" }],
"start_time": "70.15",
"end_time": "70.559",
"speaker_label": "spk_1"
},
{
"id": 168,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.971", "content": "も" }],
"start_time": "70.559",
"end_time": "70.68",
"speaker_label": "spk_1"
},
{
"id": 169,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "ご" }],
"start_time": "70.68",
"end_time": "70.83",
"speaker_label": "spk_1"
},
{
"id": 170,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "確認" }],
"start_time": "70.83",
"end_time": "71.519",
"speaker_label": "spk_1"
},
{
"id": 171,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.983", "content": "ください。" }],
"start_time": "71.519",
"end_time": "72.04",
"speaker_label": "spk_1"
},
{
"id": 172,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.998", "content": "承知" }],
"start_time": "72.4",
"end_time": "72.819",
"speaker_label": "spk_0"
},
{
"id": 173,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "し" }],
"start_time": "72.819",
"end_time": "72.9",
"speaker_label": "spk_0"
},
{
"id": 174,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "まし" }],
"start_time": "72.9",
"end_time": "73.15",
"speaker_label": "spk_0"
},
{
"id": 175,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.991", "content": "た。" }],
"start_time": "73.15",
"end_time": "73.599",
"speaker_label": "spk_0"
},
{
"id": 176,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.946", "content": "ちなみ" }],
"start_time": "73.839",
"end_time": "74.279",
"speaker_label": "spk_0"
},
{
"id": 177,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.792", "content": "に、" }],
"start_time": "74.279",
"end_time": "74.599",
"speaker_label": "spk_0"
},
{
"id": 178,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.989", "content": "再送" }],
"start_time": "74.75",
"end_time": "75.199",
"speaker_label": "spk_0"
},
{
"id": 179,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "は" }],
"start_time": "75.199",
"end_time": "75.339",
"speaker_label": "spk_0"
},
{
"id": 180,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.662", "content": "大体" }],
"start_time": "75.339",
"end_time": "75.72",
"speaker_label": "spk_0"
},
{
"id": 181,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.548", "content": "いつごろ" }],
"start_time": "75.72",
"end_time": "76.199",
"speaker_label": "spk_0"
},
{
"id": 182,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.998", "content": "に" }],
"start_time": "76.199",
"end_time": "76.309",
"speaker_label": "spk_0"
},
{
"id": 183,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "なり" }],
"start_time": "76.309",
"end_time": "76.48",
"speaker_label": "spk_0"
},
{
"id": 184,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "ます" }],
"start_time": "76.48",
"end_time": "76.68",
"speaker_label": "spk_0"
},
{
"id": 185,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.965", "content": "か。" }],
"start_time": "76.68",
"end_time": "77.199",
"speaker_label": "spk_0"
},
{
"id": 186,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.995", "content": "目安" }],
"start_time": "77.44",
"end_time": "77.83",
"speaker_label": "spk_1"
},
{
"id": 187,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "に" }],
"start_time": "77.83",
"end_time": "77.959",
"speaker_label": "spk_1"
},
{
"id": 188,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.998", "content": "は" }],
"start_time": "77.959",
"end_time": "78.11",
"speaker_label": "spk_1"
},
{
"id": 189,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "なり" }],
"start_time": "78.11",
"end_time": "78.279",
"speaker_label": "spk_1"
},
{
"id": 190,
"type": "pronunciation",
"alternatives": [{ "confidence": "1.0", "content": "ます" }],
"start_time": "78.279",
"end_time": "78.55",
"speaker_label": "spk_1"
},
{
"id": 191,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.923", "content": "が、" }],
"start_time": "78.55",
"end_time": "78.849",
"speaker_label": "spk_1"
},
{
"id": 192,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.994", "content": "夕方" }],
"start_time": "78.849",
"end_time": "79.389",
"speaker_label": "spk_1"
},
{
"id": 193,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.642", "content": "ごろ" }],
"start_time": "79.389",
"end_time": "79.65",
"speaker_label": "spk_1"
},
{
"id": 194,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.99", "content": "ま" }],
"start_time": "79.65",
"end_time": "79.8",
"speaker_label": "spk_1"
},
{
"id": 195,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.992", "content": "で" }],
"start_time": "79.8",
"end_time": "79.919",
"speaker_label": "spk_1"
},
{
"id": 196,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.995", "content": "に" }],
"start_time": "79.919",
"end_time": "80.04",
"speaker_label": "spk_1"
},
{
"id": 197,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.998", "content": "は" }],
"start_time": "80.04",
"end_time": "80.199",
"speaker_label": "spk_1"
},
{
"id": 198,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "お" }],
"start_time": "80.199",
"end_time": "80.269",
"speaker_label": "spk_1"
},
{
"id": 199,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.997", "content": "届け" }],
"start_time": "80.269",
"end_time": "80.629",
"speaker_label": "spk_1"
},
{
"id": 200,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.998", "content": "できる" }],
"start_time": "80.629",
"end_time": "81.01",
"speaker_label": "spk_1"
},
{
"id": 201,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.997", "content": "見込み" }],
"start_time": "81.01",
"end_time": "81.44",
"speaker_label": "spk_1"
},
{
"id": 202,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.992", "content": "です。" }],
"start_time": "81.44",
"end_time": "82.199",
"speaker_label": "spk_0"
},
{
"id": 203,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.757", "content": "分かり" }],
"start_time": "82.51",
"end_time": "82.669",
"speaker_label": "spk_0"
},
{
"id": 204,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "まし" }],
"start_time": "82.669",
"end_time": "82.91",
"speaker_label": "spk_0"
},
{
"id": 205,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.934", "content": "た。" }],
"start_time": "82.91",
"end_time": "83.36",
"speaker_label": "spk_0"
},
{
"id": 206,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.998", "content": "ありがとう" }],
"start_time": "83.589",
"end_time": "84.199",
"speaker_label": "spk_0"
},
{
"id": 207,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.998", "content": "ござい" }],
"start_time": "84.199",
"end_time": "84.4",
"speaker_label": "spk_0"
},
{
"id": 208,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.968", "content": "ます。" }],
"start_time": "84.4",
"end_time": "85.0",
"speaker_label": "spk_0"
},
{
"id": 209,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.997", "content": "よろしく" }],
"start_time": "85.279",
"end_time": "85.79",
"speaker_label": "spk_0"
},
{
"id": 210,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "お" }],
"start_time": "85.79",
"end_time": "86.029",
"speaker_label": "spk_0"
},
{
"id": 211,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "願い" }],
"start_time": "86.029",
"end_time": "86.25",
"speaker_label": "spk_0"
},
{
"id": 212,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.997", "content": "し" }],
"start_time": "86.25",
"end_time": "86.389",
"speaker_label": "spk_0"
},
{
"id": 213,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.985", "content": "ます。" }],
"start_time": "86.389",
"end_time": "87.04",
"speaker_label": "spk_1"
},
{
"id": 214,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "こちら" }],
"start_time": "87.309",
"end_time": "87.699",
"speaker_label": "spk_1"
},
{
"id": 215,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.658", "content": "こそ、" }],
"start_time": "87.699",
"end_time": "88.11",
"speaker_label": "spk_1"
},
{
"id": 216,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.996", "content": "よろしく" }],
"start_time": "88.11",
"end_time": "88.599",
"speaker_label": "spk_1"
},
{
"id": 217,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "お" }],
"start_time": "88.599",
"end_time": "88.839",
"speaker_label": "spk_1"
},
{
"id": 218,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.999", "content": "願い" }],
"start_time": "88.839",
"end_time": "89.08",
"speaker_label": "spk_1"
},
{
"id": 219,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.963", "content": "いたし" }],
"start_time": "89.08",
"end_time": "89.319",
"speaker_label": "spk_1"
},
{
"id": 220,
"type": "pronunciation",
"alternatives": [{ "confidence": "0.979", "content": "ます。" }],
"start_time": "89.319",
"end_time": "89.669",
"speaker_label": "spk_1"
}
],
"audio_segments": [
{
"id": 0,
"transcript": "もしもし、お世話になっております。ヤマダタロウと申します。",
"start_time": "0.0",
"end_time": "5.4",
"speaker_label": "spk_0",
"items": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12]
},
{
"id": 1,
"transcript": "お電話ありがとうございます。防災サービス窓口の担当",
"start_time": "5.55",
"end_time": "9.779",
"speaker_label": "spk_1",
"items": [13, 14, 15, 16, 17, 18, 19, 20, 21, 22]
},
{
"id": 2,
"transcript": "です。すみません、登録確認のメールを削除してしまいまして、再送が可能か確認したくてお電話しました。",
"start_time": "9.779",
"end_time": "18.879",
"speaker_label": "spk_0",
"items": [
23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39,
40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50
]
},
{
"id": 3,
"transcript": "はい、承知しました。念のため、ご本人確認をさせてください。お名前はヤマダタロウさんでお間違いないでしょうか。",
"start_time": "19.159",
"end_time": "27.92",
"speaker_label": "spk_1",
"items": [
51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67,
68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78
]
},
{
"id": 4,
"transcript": "はい、ヤマダタロウです。",
"start_time": "28.2",
"end_time": "29.909",
"speaker_label": "spk_0",
"items": [79, 80, 81, 82]
},
{
"id": 5,
"transcript": "ありがとうございます。それでは、ご登録の電話番号をお願いいたします。",
"start_time": "30.219",
"end_time": "35.88",
"speaker_label": "spk_1",
"items": [
83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98
]
},
{
"id": 6,
"transcript": "はい。09012345678",
"start_time": "36.29",
"end_time": "40.099",
"speaker_label": "spk_0",
"items": [99, 100]
},
{
"id": 7,
"transcript": "です。復唱いたします。09012345678ですね。続いて、メールアドレスをお願いいたし",
"start_time": "40.099",
"end_time": "49.099",
"speaker_label": "spk_1",
"items": [
101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114,
115
]
},
{
"id": 8,
"transcript": "ます。ヤマダタロウアットエグザンプル.comです。",
"start_time": "49.099",
"end_time": "54.38",
"speaker_label": "spk_0",
"items": [116, 117, 118, 119, 120, 121, 122, 123]
},
{
"id": 9,
"transcript": "ありがとうございます。では、内容を確認いたしますので、少々お待ちください。",
"start_time": "54.58",
"end_time": "60.009",
"speaker_label": "spk_1",
"items": [
124, 125, 126, 127, 128, 129, 130, 131, 132, 133, 134, 135, 136, 137,
138, 139
]
},
{
"id": 10,
"transcript": "はい、お願いします。",
"start_time": "60.439",
"end_time": "62.31",
"speaker_label": "spk_0",
"items": [140, 141, 142, 143, 144]
},
{
"id": 11,
"transcript": "お待たせいたしました。確認メールは本日中に再送いたします。届かない場合は、迷惑メールフォルダもご確認ください。",
"start_time": "62.569",
"end_time": "72.04",
"speaker_label": "spk_1",
"items": [
145, 146, 147, 148, 149, 150, 151, 152, 153, 154, 155, 156, 157, 158,
159, 160, 161, 162, 163, 164, 165, 166, 167, 168, 169, 170, 171
]
},
{
"id": 12,
"transcript": "承知しました。ちなみに、再送は大体いつごろになりますか。",
"start_time": "72.4",
"end_time": "77.199",
"speaker_label": "spk_0",
"items": [
172, 173, 174, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185
]
},
{
"id": 13,
"transcript": "目安にはなりますが、夕方ごろまでにはお届けできる見込み",
"start_time": "77.44",
"end_time": "81.44",
"speaker_label": "spk_1",
"items": [
186, 187, 188, 189, 190, 191, 192, 193, 194, 195, 196, 197, 198, 199,
200, 201
]
},
{
"id": 14,
"transcript": "です。分かりました。ありがとうございます。よろしくお願いし",
"start_time": "81.44",
"end_time": "86.389",
"speaker_label": "spk_0",
"items": [202, 203, 204, 205, 206, 207, 208, 209, 210, 211, 212]
},
{
"id": 15,
"transcript": "ます。こちらこそ、よろしくお願いいたします。",
"start_time": "86.389",
"end_time": "89.699",
"speaker_label": "spk_1",
"items": [213, 214, 215, 216, 217, 218, 219, 220]
}
]
}
}
Lambda で整形 + 翻訳後のファイル
文字起こし後のファイルを整形した後のEXCELファイルです。
EXCELにしているのは、Glue DataBrew のインプット形式の一部にEXCELがあるからです。
| start_time | end_time | speaker_label | text | text_en |
|---|---|---|---|---|
| 0 | 5.4 | spk_0 | もしもし、お世話になっております。ヤマダタロウと申します。 | Hello, I'm indebted to you. My name is Yamada Taro. |
| 5.55 | 9.779 | spk_1 | お電話ありがとうございます。防災サービス窓口の担当 | Thank you for calling. Person in charge of the disaster prevention service desk |
| 9.779 | 18.879 | spk_0 | です。すみません、登録確認のメールを削除してしまいまして、再送が可能か確認したくてお電話しました。 | That's it. Sorry, I deleted the registration confirmation email, and I called to check if it was possible to resend it. |
| 19.159 | 27.92 | spk_1 | はい、承知しました。念のため、ご本人確認をさせてください。お名前はヤマダタロウさんでお間違いないでしょうか。 | Yes, I understand. Just in case, let me verify your identity. Are you sure your name is Yamada Taro? |
| 28.2 | 29.909 | spk_0 | はい、ヤマダタロウです。 | Yes, it's Yamada Taro. |
| 30.219 | 35.88 | spk_1 | ありがとうございます。それでは、ご登録の電話番号をお願いいたします。 | Thank you very much. Well then, please give us your registered phone number. |
| 36.29 | 40.099 | spk_0 | はい。09012345678 | Yes. 09012345678 |
| 40.099 | 49.099 | spk_1 | です。復唱いたします。09012345678ですね。続いて、メールアドレスをお願いいたし | That's it. I will sing it again. 09012345678, isn't it? Next, I asked for an email address |
| 49.099 | 54.38 | spk_0 | ます。ヤマダタロウアットエグザンプル.comです。 | I'll do it. This is Yamada Taro at Example.Com. |
| 54.58 | 60.009 | spk_1 | ありがとうございます。では、内容を確認いたしますので、少々お待ちください。 | Thank you very much. Now, let's check the details, so please wait a moment. |
| 60.439 | 62.31 | spk_0 | はい、お願いします。 | Yes, please. |
| 62.569 | 72.04 | spk_1 | お待たせいたしました。確認メールは本日中に再送いたします。届かない場合は、迷惑メールフォルダもご確認ください。 | Thank you for waiting. The confirmation email will be sent again later today. If you don't receive it, check your spam folder as well. |
| 72.4 | 77.199 | spk_0 | 承知しました。ちなみに、再送は大体いつごろになりますか。 | I understand that. By the way, when will it usually be re-sent? |
| 77.44 | 81.44 | spk_1 | 目安にはなりますが、夕方ごろまでにはお届けできる見込み | As a guide, it is expected to be delivered by around evening |
| 81.44 | 86.389 | spk_0 | です。分かりました。ありがとうございます。よろしくお願いし | That's it. Understood. Thank you very much. Thank you for your support |
| 86.389 | 89.699 | spk_1 | ます。こちらこそ、よろしくお願いいたします。 | I'll do it. Thank you very much for your support. |
マスキング後のファイル
Glue DataBrew でマスキングされた後のファイルです。
出力ファイル形式は CSV です。
| start_time | end_time | speaker_label | text | text_en |
|---|---|---|---|---|
| 0 | 5.4 | spk_0 | もしもし、お世話になっております。ヤマダタロウと申します。 | Hello, I'm indebted to you. My name is ###### ####. |
| 5.55 | 9.779 | spk_1 | お電話ありがとうございます。防災サービス窓口の担当 | Thank you for calling. Person in charge of the disaster prevention service desk |
| 9.779 | 18.879 | spk_0 | です。すみません、登録確認のメールを削除してしまいまして、再送が可能か確認したくてお電話しました。 | That's it. Sorry, I deleted the registration confirmation email, and I called to check if it was possible to resend it. |
| 19.159 | 27.92 | spk_1 | はい、承知しました。念のため、ご本人確認をさせてください。お名前はヤマダタロウさんでお間違いないでしょうか。 | Yes, I understand. Just in case, let me verify your identity. Are you sure your name is ###### ####? |
| 28.2 | 29.909 | spk_0 | はい、ヤマダタロウです。 | Yes, it's ###### ####. |
| 30.219 | 35.88 | spk_1 | ありがとうございます。それでは、ご登録の電話番号をお願いいたします。 | Thank you very much. Well then, please give us your registered phone number. |
| 36.29 | 40.099 | spk_0 | はい。09012345678 | Yes. ##### |
| 40.099 | 49.099 | spk_1 | です。復唱いたします。09012345678ですね。続いて、メールアドレスをお願いいたし | That's it. I will sing it again. #####, isn't it? Next, I asked for an email address |
| 49.099 | 54.38 | spk_0 | ます。ヤマダタロウアットエグザンプル.comです。 | I'll do it. This is ###### #### #####. |
| 54.58 | 60.009 | spk_1 | ありがとうございます。では、内容を確認いたしますので、少々お待ちください。 | Thank you very much. ###, let's check the details, so please wait a moment. |
| 60.439 | 62.31 | spk_0 | はい、お願いします。 | Yes, please. |
| 62.569 | 72.04 | spk_1 | お待たせいたしました。確認メールは本日中に再送いたします。届かない場合は、迷惑メールフォルダもご確認ください。 | Thank you for waiting. The confirmation email will be sent again ##### #####. If you don't receive it, check your spam folder as well. |
| 72.4 | 77.199 | spk_0 | 承知しました。ちなみに、再送は大体いつごろになりますか。 | I understand that. By the way, when will it usually be re-sent? |
| 77.44 | 81.44 | spk_1 | 目安にはなりますが、夕方ごろまでにはお届けできる見込み | As a guide, it is expected to be delivered by around evening |
| 81.44 | 86.389 | spk_0 | です。分かりました。ありがとうございます。よろしくお願いし | That's it. Understood. Thank you very much. Thank you for your support |
| 86.389 | 89.699 | spk_1 | ます。こちらこそ、よろしくお願いいたします。 | I'll do it. Thank you very much for your support. |
最終出力ファイル
Lambda で整形した後のテキストファイルです。
内部的にはマスキングした各英文を Translate SDK で日本語翻訳して時系列に整形しています。
[Speaker: spk_0]
こんにちは、お世話になりました。私の名前は ###### ### です。
[Speaker: spk_1]
電話してくれてありがとう。防災サービスデスクの担当者
[Speaker: spk_0]
それだけです。申し訳ありませんが、登録確認メールを削除しました。再送信できるかどうかを確認するために電話をかけました。
[Speaker: spk_1]
はい、わかりました。念のため、あなたの本人確認をさせてください。本当にあなたの名前は ###### ### ですか？
[Speaker: spk_0]
はい、###### ###です。
[Speaker: spk_1]
どうもありがとうございます。それでは、登録している電話番号を教えてください。
[Speaker: spk_0]
はい。#####
[Speaker: spk_1]
それだけです。また歌います。##### ですよね？次に、メールアドレスを尋ねました
[Speaker: spk_0]
私はそれをします。これは ####### ### ####です。
[Speaker: spk_1]
ありがとうございます。###、詳細を確認しますので、ちょっと待ってください。
[Speaker: spk_0]
はい、お願いします。
[Speaker: spk_1]
お待たせしました。確認メールが再度送信されます###### ###。届かない場合は、迷惑メールフォルダも確認してください。
[Speaker: spk_0]
それは分かりますよ。ところで、通常いつ再送されますか？
[Speaker: spk_1]
目安ですが、夕方頃までに届く予定です
[Speaker: spk_0]
それだけです。分かりましたよ。どうもありがとうございます。ご支援いただきありがとうございます
[Speaker: spk_1]
私はそれをします。ご支援いただきありがとうございます。
おわりに
本記事では、Amazon Transcribe と AWS Glue DataBrew で日本語音声ファイルの文字起こしとマスキングを実装してみました。
正直微妙な結果になってしまいましたが、１ミリでも誰かの参考になればと思い記事にしました。
🌟この記事が誰かの役に立てば幸いです！
また、ご質問やフィードバックもお待ちしています。
参考資料
リファレンス
- Step Functions の入力および出力処理 - AWS Step Functions デベロッパーガイド
- Amazon Polly とは - Amazon Polly デベロッパーガイド
- aws-samples/automating-pii-data-detection-and-data-masking-tasks-with-aws-glue-databrew-and-aws-step-functions - GitHub
ブログ
- サーバーレス時代のPII対策！AWS Glue ETLで実現する個人情報の自動検出とマスキング実装
- AWS Glue DataBrewで個人情報(PII)の検出とデータマスキング変換が出来るようになったようなので試してみた - DevelopersIO
- AWS Glue DataBrewで個人を特定できる情報 (PII) の検出と変換処理を試す - Qiita
- AWS Glue Databrewを利用した個人データ自動マスキングのデータパイプラインを検証してみた - DevelopersIO
- Glue DataBrew のハンズオンをやって操作感を掴んでみた & Athena 経由で加工済みデータを QuickSight で可視化してみた - DevelopersIO