SPEAKER DIARIZATION METHOD, SYSTEM, AND COMPUTER PROGRAM COUPLED WITH SPEAKER IDENTIFICATION

To provide a speaker diarization method, system and computer program coupled with speaker identification.SOLUTION: A speaker diarization method includes the steps of: setting a reference voice in relation to a voice file received from a client as a speaker diarization target voice; performing speake...

Full description

Saved in:
Bibliographic Details
Main Authors HAN ICKSANG, KANG HAN YONG, HEO HEE SOO, KIM YOU JIN, KWON YOUNGKI, LEE BONG JIN, JANG JUNGHOON, KIM HAN KYU, CHUNG JOON SON
Format Patent
LanguageEnglish
Japanese
Published 28.07.2022
Subjects
ACOUSTICS
MUSICAL INSTRUMENTS
PHYSICS
SPEECH ANALYSIS OR SYNTHESIS
SPEECH OR AUDIO CODING OR DECODING
SPEECH OR VOICE PROCESSING
SPEECH RECOGNITION
Online AccessGet full text

Cover

More Information
Summary:To provide a speaker diarization method, system and computer program coupled with speaker identification.SOLUTION: A speaker diarization method includes the steps of: setting a reference voice in relation to a voice file received from a client as a speaker diarization target voice; performing speaker identification to identify a speaker of the reference voice from the voice file using the reference voice; and performing speaker diarization using clustering for remaining speech segments that were not identified by the voice file.SELECTED DRAWING: Figure 7 【課題】 話者識別を結合した話者ダイアライゼーション方法、システム、およびコンピュータプログラムを提供する。【解決手段】 話者ダイアライゼーション方法は、クライアントから話者ダイアライゼーション対象音声として受信された音声ファイルと関連して基準音声を設定する段階、前記基準音声を利用して前記音声ファイルから前記基準音声の話者を識別する話者識別を実行する段階、および前記音声ファイルで識別されなかった残りの発話区間に対して、クラスタリングを利用した話者ダイアライゼーションを実行する段階を含む。【選択図】図７
Bibliography:Application Number: JP20210189143