Mandarin speech recognition using segment-based cepstral comparison in noisy conditions

Shin Lun Tung, Yau Tarng Juang

Research output: Contribution to journalArticlepeer-review

Abstract

A new scheme is proposed that compensates for the effects of noise in speech recognition systems. The new scheme was applied to Mandarin speech recognition. Another scheme, based on interpolation of the compensation vectors of several environments for a particular environment that is not obtained during the training phase, called interpolated SSDCN (ISSDCN), is also presented. Experimental results show that the scheme performs well under different SNR conditions.

Original languageEnglish
Pages (from-to)XV-1543
JournalElectronics Letters
Volume32
Issue number17
DOIs
StatePublished - 1996

Keywords

  • Cepstral analysis
  • Speech recognition

Fingerprint

Dive into the research topics of 'Mandarin speech recognition using segment-based cepstral comparison in noisy conditions'. Together they form a unique fingerprint.

Cite this