|
Edinburgh Research Archive >
Centre for Speech Technology Research >
CSTR publications >
Please use this identifier to cite or link to this item:
http://hdl.handle.net/1842/954
|
| Title: | Connectionist Speech Recognition of Broadcast News |
| Authors: | Robinson, A J
Cook, Gary
Ellis, Dan
Fosler-Lussier, Eric
Renals, Steve
Williams, D A G |
| Issue Date: | May-2002 |
| Citation: | Speech Communication, 37:27-45, 2002 |
| Publisher: | Elsevier Science B.V. |
| 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. |
| Keywords: | Speech Recognition
Neural networks
Acoustic features
Pronunciation modelling
Search techniques
Stack decoder |
| URI: | doi:10.1016/S0167-6393(01)00058-9
http://hdl.handle.net/1842/954 |
| Appears in Collections: | CSTR publications
|
Items in ERA are protected by copyright, with all rights reserved, unless otherwise indicated.
|
