Title:

Connectionist Speech Recognition of Broadcast News

Author(s):

Robinson, A. J.
Cook, G. D.
Ellis, Daniel P. W.
Fosler-Lussier, Eric
Renals, S. J.
Williams, D. A. G.

Date:

2002

Type:

Articles

Department:

Electrical Engineering

Volume:

37

Permanent URL:

http://hdl.handle.net/10022/AC:P:12568

Book/Journal Title:

Speech Communication

Abstract:

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.

Subject(s):

Artificial intelligence
Communication

DOI:

http://dx.doi.org/10.1016/S0167-6393(01)00058-9

Item views:

27

Metadata:

description

View | Download