Exploiting spatial-temporal feature distribution characteristics for robust speech recognition

Wei Hau Chen*, Shih Hsiang Lin, Berlin Chen

*此作品的通信作者

研究成果: 雜誌貢獻會議論文同行評審

3 引文 斯高帕斯(Scopus)

摘要

Noise robustness is one of the primary challenges facing most automatic speech recognition (ASR) systems. Quite several speech feature histogram equalization (HEQ) methods have been developed to compensate for nonlinear noise distortions. However, most of the current HEQ methods are merely performed in a dimension-wise manner and without taking into consideration the contextual relationships between consecutive speech frames. In this paper, we present a novel HEQ approach that exploits spatial-temporal feature distribution characteristics for speech feature normalization. All experiments were carried out on the Aurora-2 database and task. The performance of the presented approach is tested and verified by comparison with the other HEQ methods. The experiment results show that for clean-condition training, our method yields a significant word error rate reduction over the baseline system, and also considerably outperforms the other HEQ methods compared in this paper.

原文英語
頁(從 - 到)2004-2007
頁數4
期刊Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
出版狀態已發佈 - 2008 十二月 1
事件INTERSPEECH 2008 - 9th Annual Conference of the International Speech Communication Association - Brisbane, QLD, 澳大利亚
持續時間: 2008 九月 222008 九月 26

ASJC Scopus subject areas

  • 人機介面
  • 訊號處理
  • 軟體
  • 感覺系統

指紋

深入研究「Exploiting spatial-temporal feature distribution characteristics for robust speech recognition」主題。共同形成了獨特的指紋。

引用此