Connectionist speech recognition of Broadcast News

被引：18

作者：

Robinson, AJ

Cook, GD

Ellis, DPW

Fosler-Lussier, E

Renals, SJ

Williams, DAG

机构：

[1] SoftSound Ltd, Autonomy Syst Ltd, Cambridge CB4 0WS, England

[2] Phonet Syst UK Ltd, Cheltenham GL52 8RW, Glos, England

[3] Columbia Univ, Dept Elect Engn, New York, NY 10027 USA

[4] Bell Labs, Lucent Technol, Murray Hill, NJ 07974 USA

[5] Univ Sheffield, Dept Comp Sci, Sheffield S1 4DP, S Yorkshire, England

[6] Univ Cambridge, Dept Engn, Cambridge CB2 1PZ, England

[7] Int Comp Sci Inst, Berkeley, CA 94704 USA

来源：

SPEECH COMMUNICATION | 2002年 / 37卷 / 1-2期

关键词：

speech recognition; neural networks; acoustic features; pronunciation modelling; search techniques; stack decoder;

D O I：

10.1016/S0167-6393(01)00058-9

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

This paper describes connectionist techniques for recognition of Broadcast News. The fundamental difference between connectionist systems and more conventional mixture-of-Gaussian systems is that connectionist models directly estimate posterior probabilities as opposed to likelihoods. Access to posterior probabilities has enabled us to develop a number of novel approaches to confidence estimation, pronunciation modelling and search. In addition we have investigated a new feature extraction technique based on the modulation-filtered spectrogram (MSG), and methods for combining multiple information sources. We have incorporated all of these techniques into a system for the transcription of Broadcast News, and we present results on the 1998 DARPA Hub-4E Broadcast News evaluation data. (C) 2002 Elsevier Science B.V. All rights reserved.

引用

页码：27 / 45

页数：19

共 50 条

[1]

[Anonymous], 1980, TRENDS SPEECH RECOGN

[2]

[Anonymous], 1996, Automatic Speech and Speaker Recognition

[3]

BARKER J, 1998, P INT C SPOK LANG PR, P2719

[4]

BERNARDIS G, 1998, P INT C SPOK LANG PR, P775

[5]

BOURLARD H, 1996, AUTOMATIC SPEECH SPE, P259

[6]

BOURLARD H, 1994, P IEEE INT C AC SPEE, P373

[7]

CLARKSON P, 1997, EUR C SPEECH COMM TE, P2707

[8]

Cook G, 1998, INT CONF ACOUST SPEE, P917, DOI 10.1109/ICASSP.1998.675415

[9]

COOK G, 1997, P DARPA SPEECH REC W, P79

[10]

COX S, 1996, P INT C AC SPEECH SI, P511

← 1 2 3 4 5 →