Artigo Acesso aberto Revisado por pares

Connectionist speech recognition of Broadcast News

2002; Elsevier BV; Volume: 37; Issue: 1-2 Linguagem: Inglês

10.1016/s0167-6393(01)00058-9

ISSN

1872-7182

Autores

A.J. Robinson, Gary Cook, Daniel P. W. Ellis, Eric Fosler‐Lussier, Steve Renals, Dominic Williams,

Tópico(s)

Speech and Audio Processing

Resumo

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.

Referência(s)