Modeling those F-conditions - or not (1997) [13 citations — 0 self]
Download:
|
|
by Richard Schwartz, Hubert Jin, Francis Kubala, Yspyros Matsoukas
Proc. DARPA Speech Recognition Workshop
http://www.itl.nist.gov/iaui/894.01/proc/darpa97/ps/schwart1.ps
Add To MetaCart
Popular Tags
No tags have been applied to this document.
BibTeX | Add To MetaCart
@INPROCEEDINGS{Schwartz97modelingthose,author = {Richard Schwartz and Hubert Jin and Francis Kubala and Yspyros Matsoukas},
title = {Modeling those F-conditions - or not},
booktitle = {Proc. DARPA Speech Recognition Workshop},
year = {1997},
pages = {115--118}
}
Years of Citing Articles
Abstract:
After several disappointing preliminary attempts to make condition-specific models, we decided that it would be more advantageous to spend our time just trying to improve the core recognition system and use general adaptation techniques to deal with variations. This simplified the system immensely and freed up people and also made the transition from the PE system to the UE system much easier. We describe our attempts at condition-specific modeling /adaptation/training. We show that the benefit for channel-specific modeling is smaller than that for general adaption procedures and we argue that the cost is too high.
Citations
| 54 | A compact model for speaker adaptive training – Anastasakos, McDonough, et al. - 1996 |
| 53 | Flexible speaker adaptation using maximum likelihood linear regression – Leggetter, Woodland - 1995 |
| 45 | Segregation of speakers for speech recognition and speaker identification – Gish, Siu, et al. - 1991 |
| 20 | Automatic speaker clustering – Jin, Kubala, et al. - 1997 |
| 15 | Adaptation to new microphones using tied-mixture normalization – Anastasakos, Kubala, et al. - 1994 |
| 9 | Practical implementations of speaker-adaptive training – Matsoukas, Schwartz, et al. - 1997 |
| 4 | A Compact Model for Speaker-AdaptiveTraining – Anastasakos, McDonough, et al. - 1996 |
| 3 | elsewhere this volume – Kubala, Jin, et al. - 1997 |
| 3 | Transcription of radio broadcast news with the IBM large vocabulary speech recognition system – Gopalakrishnan - 1996 |
