A mismatch-aware stochastic matching algorithm for robust speech recognition

Yuan Fu Liao*, Jeng Shien Lin, Sin-Horng Chen

*Corresponding author for this work

Research output: Contribution to journalConference article

Abstract

In this paper, we present a mismatch-aware stochastic matching (MASM) algorithm to alleviate the performance degradation under mismatched training and testing conditions. MASM first computes a reliability measure of applying a set of pre-trained speech models to a mismatch test utterance along the time axis or among different feature vector components. It then estimates and compensates the mismatch using the reliability measure to guide the speech segmentation. Experiments on a serious mismatched condition with training on PSTN-speech database and testing on mobile GSM-speech database showed that MASM outperformed the stochastic match (SM) method, especially, for short utterances.

Original languageEnglish
Pages (from-to)101-104
Number of pages4
JournalICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2
DOIs
StatePublished - 25 Sep 2003
Event2003 IEEE International Conference on Accoustics, Speech, and Signal Processing - Hong Kong, Hong Kong
Duration: 6 Apr 200310 Apr 2003

Fingerprint Dive into the research topics of 'A mismatch-aware stochastic matching algorithm for robust speech recognition'. Together they form a unique fingerprint.

  • Cite this