Academic Commons

Articles

Connectionist Speech Recognition of Broadcast News

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

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.

Files

  • thumnail for S0167-6393_01_00058-9.pdf S0167-6393_01_00058-9.pdf application/x-pdf 266 KB Download File

Also Published In

Title
Speech Communication
DOI
https://doi.org/10.1016/S0167-6393(01)00058-9

More About This Work

Academic Units
Electrical Engineering
Published Here
February 15, 2012
Academic Commons provides global access to research and scholarship produced at Columbia University, Barnard College, Teachers College, Union Theological Seminary and Jewish Theological Seminary. Academic Commons is managed by the Columbia University Libraries.