Sciweavers

Share
ICASSP
2010
IEEE

Discriminative template extraction for direct modeling

9 years 4 months ago
Discriminative template extraction for direct modeling
This paper addresses the problem of developing appropriate features for use in direct modeling approaches to speech recognition, such as those based on Maximum Entropy models or Segmental Conditional Random Fields. We propose a feature based on the detection of word-level templates which are discriminatively chosen based on a mutual information criterion. The templates for a word are derived directly from the MFCC feature vectors, based on self-similarity across examples. No pronunciation dictionary is used, and the resulting templates match closely to in-class examples and distantly to out-of-class examples. We utilize template detection events as input to a segmental CRF speech recognizer. We evaluate the entire scheme on a voice search task. The results show that the use of discriminative template based word detector streams improves the speech recognizer’s performance over the baseline HMM results.
Shankar Shivappa, Patrick Nguyen, Geoffrey Zweig
Added 06 Dec 2010
Updated 06 Dec 2010
Type Conference
Year 2010
Where ICASSP
Authors Shankar Shivappa, Patrick Nguyen, Geoffrey Zweig
Comments (0)
books