Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
| Paper: | SP-P12.9 |
| 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: |
PHONE DURATION MODELING FOR LVCSR |
| Authors: |
Daniel Povey; IBM T. J. Watson Research Center | | |
| Abstract: |
Modeling phone durations in a word-specific fashion has previously been shown to lead to improvements in LVCSR recognition performance. We report results on the Switchboard database which confirm that at least small improvements (around 0.2-0.3% absolute) can be obtained. The duration probabilities are applied to time-marked recognition lattices. Features of the system include a novel data-driven method for smoothing discrete distributions, and a form of discrete distribution which allows phone and word lengths to be modeled simultaneously within a consistent probabilitic framework. |
| |
| Back | |