Automatic named identification of speakers using diarization and ASR systems

Vincent Jousse,Simon Petit-Renaud,Sylvain Meignier,Yannick Esteve,Christine Jacquin

Taipei（2009）

引用 45|浏览1

暂无评分

摘要

In this paper, we consider the extraction of speaker identity from audio records of broadcast news without a priori acoustic information about speakers. Using an automatic speech recognition system and an automatic speaker diarization system, we present improvements for a method which allows to extract speaker identities from automatic transcripts and to assign them to speech segments. Experiments are carried out on French broadcast news records from the ESTER 1 evaluation campaign. Experimental results using outputs of automatic speech recognition and automatic diarization are presented.

查看译文

关键词

asr system,speaker diariza- tion,automatic speech recognition,speaker identity,automatic speaker diarization system,speech segment,audio record,automatic transcript,index terms— named identification,automatic speech recognition system,automatic diarization,broadcast news,french broadcast news record,automatic transcription,information retrieval,indexing,natural language processing,broadcasting,speaker diarization,data mining,speaker recognition,speech,loudspeakers,audio signal processing,speech segmentation,acoustics,probability density function,speech recognition,indexing terms,training data

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要