A mismatch-aware stochastic matching algorithm for robust speech recognition

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

*Corresponding author for this work

研究成果: Conference article

摘要

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.

原文English
頁(從 - 到)101-104
頁數4
期刊ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
2
DOIs
出版狀態Published - 25 九月 2003
事件2003 IEEE International Conference on Accoustics, Speech, and Signal Processing - Hong Kong, Hong Kong
持續時間: 6 四月 200310 四月 2003

指紋 深入研究「A mismatch-aware stochastic matching algorithm for robust speech recognition」主題。共同形成了獨特的指紋。

  • 引用此