Cluster-based polynomial-fit histogram equalization (CPHEQ) for robust speech recognition

Shih Hsiang Lin, Yao Ming Yeh, Berlin Chen

研究成果: 書貢獻/報告類型會議貢獻

1 引文 斯高帕斯(Scopus)

摘要

Noise robustness is one of the primary challenges facing most automatic speech recognition (ASR) systems. A vast amount of research efforts on preventing the degradation of ASR performance under various noisy environments have been made during the past several years. In this paper, we consider the use of histogram equalization (HEQ) for robust ASR. In contrast to conventional methods, a novel data fitting method based on polynomial regression was presented to efficiently approximate the inverse of the cumulative density functions of speech feature vectors for HEQ. Moreover, a more elaborate attempt of using such polynomial regression models to directly characterizing the relationship between the speech feature vectors and their corresponding probability distributions, under various noise conditions, was proposed as well. All experiments were carried out on the Aurora-2 database and task. The performance of the presented methods were extensively tested and verified by comparison with the other methods. Experimental results shown that for cleancondition training, our method achieved a considerable word error rate reduction over the baseline system, and also significantly outperformed the other methods.

原文英語
主出版物標題International Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007
發行者Unavailable
頁面197-200
頁數4
ISBN(列印)9781605603162
出版狀態已發佈 - 2007 一月 1
事件8th Annual Conference of the International Speech Communication Association, Interspeech 2007 - Antwerp, 比利时
持續時間: 2007 八月 272007 八月 31

出版系列

名字Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
1
ISSN(電子)1990-9772

其他

其他8th Annual Conference of the International Speech Communication Association, Interspeech 2007
國家比利时
城市Antwerp
期間07/8/2707/8/31

ASJC Scopus subject areas

  • Computer Science Applications
  • Software
  • Modelling and Simulation
  • Linguistics and Language
  • Communication
  • Management, Monitoring, Policy and Law
  • Renewable Energy, Sustainability and the Environment
  • Energy(all)
  • Energy Engineering and Power Technology
  • Fuel Technology

指紋 深入研究「Cluster-based polynomial-fit histogram equalization (CPHEQ) for robust speech recognition」主題。共同形成了獨特的指紋。

引用此