A multi-filter system for speech enhancement under low signal-to-noise ratios

Ka Fai Cedric Yiu, K. Y. Chan, S. Y. Low, S. Nordholm

Research output: Journal article publicationJournal articleAcademic researchpeer-review

10 Citations (Scopus)


In this paper, the problem of deteriorating performance of speech recognition under very low signal-to-noise ratios (SNR) is considered. In particular, for a given pre-trained speech recognizer and for a finite set of speech commands, we show that popular noise reduction methods have a mixed performance in speech recognition accuracy under very low SNR. Although most noise reduction methods are attempting to reduce speech distortion or to increase noise suppression, it does not necessarily improve speech recognition accuracy very much due to the complexity of the recognizer. We propose a new hybrid algorithm to optimize on the speech recognition accuracy directly by mixing different noise reduction methods together. We show that this method can indeed improve the accuracy significantly.
Original languageEnglish
Pages (from-to)671-682
Number of pages12
JournalJournal of Industrial and Management Optimization
Issue number3
Publication statusPublished - 6 Aug 2009


  • Noise reduction
  • Optimization
  • Speech echancement
  • Speech recognition

ASJC Scopus subject areas

  • Business and International Management
  • Strategy and Management
  • Control and Optimization
  • Applied Mathematics


Dive into the research topics of 'A multi-filter system for speech enhancement under low signal-to-noise ratios'. Together they form a unique fingerprint.

Cite this