Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
| Paper: | SP-P12.12 |
| Session: | Acoustic Modeling: Model Complexity, General Topics |
| Time: | Thursday, May 20, 09:30 - 11:30 |
| Presentation: |
Poster |
| Topic: |
Speech Processing: Acoustic Modeling for Speech Recognition |
| Title: |
TRAINING FOR POLYNOMIAL SEGMENT MODEL USING THE EXPECTATION MAXIMIZATION ALGORITHM |
| Authors: |
Chak-Fai Li; Hong Kong University of Science and Technology | | |
| | Man-Hung Siu; Hong Kong University of Science and Technology | | |
| Abstract: |
One of the difficulties in using polynomial segment model (PSM) to capture the temporal correlations within a phonetic segment is the lack of an efficient training algorithm comparable with the Baum-Welch algorithm in HMM. In our previous paper, we introduced a recursive likelihood computation algorithm for PSM recognition and can perform Viterbi-style training. In this paper, we extend the recurrsive likelihood computation into a fast forward-backward PSM training algorithm that maximizes PSM likelihood. In addition, we introduce an improved PSM, dynamic multi-segment PSM, that allows a data-driven alignment betweens observations and the segment trajectory. The dynamic multi-segment PSM model outperforms HMM and traditional PSM in both phone classification and phone recognition tasks on the TIMIT corpus. |
| |
| Back | |