Unsupervised speaker adaptation for telephone call transcription


Autoria(s): Wallace, Roy G.; Thambiratnam, Kit; Seide, Frank
Data(s)

2009

Resumo

The use of the PC and Internet for placing telephone calls will present new opportunities to capture vast amounts of un-transcribed speech for a particular speaker. This paper investigates how to best exploit this data for speaker-dependent speech recognition. Supervised and unsupervised experiments in acoustic model and language model adaptation are presented. Using one hour of automatically transcribed speech per speaker with a word error rate of 36.0%, unsupervised adaptation resulted in an absolute gain of 6.3%, equivalent to 70% of the gain from the supervised case, with additional adaptation data likely to yield further improvements. LM adaptation experiments suggested that although there seems to be a small degree of speaker idiolect, adaptation to the speaker alone, without considering the topic of the conversation, is in itself unlikely to improve transcription accuracy.

Formato

application/pdf

Identificador

http://eprints.qut.edu.au/29659/

Publicador

IEEE

Relação

http://eprints.qut.edu.au/29659/1/c29659.pdf

DOI:10.1109/ICASSP.2009.4960603

Wallace, Roy G., Thambiratnam, Kit, & Seide, Frank (2009) Unsupervised speaker adaptation for telephone call transcription. In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, IEEE, Taipei International Convention Center, Taipei, pp. 4393-4396.

Direitos

Copyright 2009 IEEE

Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

Fonte

Faculty of Built Environment and Engineering; Information Security Institute; School of Engineering Systems

Palavras-Chave #080107 Natural Language Processing #speaker adaptation #acoustic model adaptation #language model adaptation #unsupervised adaptation #speech recognition
Tipo

Conference Paper