Abstract
This paper presents a new training algorithm for self-structuring hidden control neural (SHC) models. The SHC models were trained non-discriminatively for speech recognition applications. Better recognition performance can generally be achieved, if discriminative training is applied instead. Thus we developed a discriminative training algorithm for SHC models, where each SHC model for a specific speech pattern is trained with utterances of the pattern to be recognized and with other utterances. The discriminative training of SHC neural models has been tested on the TIDIGITS database
Original language | English |
---|---|
Title of host publication | Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing |
Volume | Volume 5 |
Publisher | IEEE |
Publication date | 1995 |
Pages | 3379-3382 |
ISBN (Print) | 07-80-32431-5 |
DOIs | |
Publication status | Published - 1995 |
Event | 1995 IEEE International Conference on Acoustics, Speech, and Signal Processing - Detroit, United States Duration: 8 May 1995 → 12 May 1995 Conference number: 20 |
Conference
Conference | 1995 IEEE International Conference on Acoustics, Speech, and Signal Processing |
---|---|
Number | 20 |
Country/Territory | United States |
City | Detroit |
Period | 08/05/1995 → 12/05/1995 |