Paper: | SP-L8.3 | ||
Session: | Acoustic Modeling: New Search Features and Supervised Training | ||
Time: | Friday, May 21, 10:10 - 10:30 | ||
Presentation: | Lecture | ||
Topic: | Speech Processing: Acoustic Modeling for Speech Recognition | ||
Title: | JOINT DECODING FOR PHONEME-GRAPHEME CONTINUOUS SPEECH RECOGNITION | ||
Authors: | Mathew Magimai.-Doss; Dalle Molle Institute for Artificial Intelligence | ||
Samy Bengio; Dalle Molle Institute for Artificial Intelligence | |||
Hervé Bourlard; Dalle Molle Institute for Artificial Intelligence | |||
Abstract: | Standard ASR systems typically use phoneme as the subwordunits. Preliminary studies have shown that the performance of the ASR system could be improved by using grapheme as additional subword units. In this paper, we investigate such a system where the word models are defined in terms of two different subword units, i.e.,phonemes and graphemes. During training, models for both the subword units are trained, and then during recognition either both or just one subword unit is used. We have studied this system for a continuous speech recognition task in American English language. Our studies show that grapheme information used along with phoneme information improves the performance of ASR. | ||
Back |
Home -||-
Organizing Committee -||-
Technical Committee -||-
Technical Program -||-
Plenaries
Paper Submission -||-
Special Sessions -||-
ITT -||-
Paper Review -||-
Exhibits -||-
Tutorials
Information -||-
Registration -||-
Travel Insurance -||-
Housing -||-
Workshops