Publication Details
Title: Connectionist Speech Recognition: Status and Prospects
Author: S. Renals, N. Morgan, H. Bourlard, M. Cohen, H. Franco, C. Wooters, and P. Kohn
Group: ICSI Technical Reports
Date: December 1991
PDF: http://www.icsi.berkeley.edu/pubs/techreports/tr-91-070.pdf
Overview:
We report on recent advances in the ICSI connectionist speech recognition project. Highlights include: 1. Experimental results showing that connectionist methods can improve the performance of a context independent maximum likelihood trained HMM system, resulting in a performance close to that achieved using state of the art context dependent HMM systems of much higher complexity; 2. Mixing (context independent) connectionist probability estimates with maximum likelihood trained context dependent models to improve the performance of a state of the art system; 3. The development of a network decomposition method that allows connectionist modeling of context dependent phones efficiently and parsimoniously, with no statistical independence assumptions.
Bibliographic Information:
ICSI Technical Report TR-91-070
Bibliographic Reference:
S. Renals, N. Morgan, H. Bourlard, M. Cohen, H. Franco, C. Wooters, and P. Kohn. Connectionist Speech Recognition: Status and Prospects. ICSI Technical Report TR-91-070, December 1991
Author: S. Renals, N. Morgan, H. Bourlard, M. Cohen, H. Franco, C. Wooters, and P. Kohn
Group: ICSI Technical Reports
Date: December 1991
PDF: http://www.icsi.berkeley.edu/pubs/techreports/tr-91-070.pdf
Overview:
We report on recent advances in the ICSI connectionist speech recognition project. Highlights include: 1. Experimental results showing that connectionist methods can improve the performance of a context independent maximum likelihood trained HMM system, resulting in a performance close to that achieved using state of the art context dependent HMM systems of much higher complexity; 2. Mixing (context independent) connectionist probability estimates with maximum likelihood trained context dependent models to improve the performance of a state of the art system; 3. The development of a network decomposition method that allows connectionist modeling of context dependent phones efficiently and parsimoniously, with no statistical independence assumptions.
Bibliographic Information:
ICSI Technical Report TR-91-070
Bibliographic Reference:
S. Renals, N. Morgan, H. Bourlard, M. Cohen, H. Franco, C. Wooters, and P. Kohn. Connectionist Speech Recognition: Status and Prospects. ICSI Technical Report TR-91-070, December 1991