Recognition of noisy speech using dynamic spectral subband centroids

Jingdong Chen, Yiteng Arden Huang, Qi Li, Kuldip K. Paliwal

Research output: Contribution to journalArticlepeer-review

47 Scopus citations

Abstract

Despite their widespread popularity as front-end parameters for speech recognition, the cepstral coefficients derived from either linear prediction analysis or a filter-bank are found to be sensitive to additive noise. In this letter, we discuss the use of spectral subband centroids for robust speech recognition. We show that centroids, if properly selected, can achieve recognition performance comparable to that of the mel-frequency cepstral coefficients (MFCCs) in clean speech, while delivering better performance than MFCC in noisy environments. A procedure is proposed to construct the dynamic centroid feature vector that essentially embodies the transitional spectral information. We discuss some properties of the proposed dynamic features.

Original languageEnglish
Pages (from-to)258-261
Number of pages4
JournalIEEE Signal Processing Letters
Volume11
Issue number2 PART II
DOIs
StatePublished - Feb 2004
Externally publishedYes

Keywords

  • Cepstrum
  • Robust speech recognition
  • Subband centroid

Fingerprint

Dive into the research topics of 'Recognition of noisy speech using dynamic spectral subband centroids'. Together they form a unique fingerprint.

Cite this