Combining standard and throat microphones for robust speech recognition

Martin Graciarena, Horacio Franco, Kemal Sonmez, Harry Bratt

Research output: Contribution to journalArticlepeer-review

92 Scopus citations

Abstract

We present a method to combine the standard and throat microphone signals for robust speech recognition in noisy environments. Our approach is to use the probabilistic optimum filter (POF) mapping algorithm to estimate the standard microphone clean-speech feature vectors, used by standard speech recognizers, from both microphones' noisy-speech feature vectors. A small untranscribed "stereo" database (noisy and clean simultaneous recordings) is required to train the POF mappings. In continuous-speech recognition experiments using SRI International's DECIPHER recognition system, both using artificially added noise and using recorded noisy speech, the combined-microphone approach significantly outperforms the single-microphone approach.

Original languageEnglish (US)
Pages (from-to)72-74
Number of pages3
JournalIEEE Signal Processing Letters
Volume10
Issue number3
DOIs
StatePublished - Mar 2003
Externally publishedYes

Keywords

  • Noise robustness
  • Probabilistic optimum filtering
  • Speech recognition
  • Throat microphone

ASJC Scopus subject areas

  • Signal Processing
  • Applied Mathematics
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Combining standard and throat microphones for robust speech recognition'. Together they form a unique fingerprint.

Cite this