Leveraging distributional characteristics of modulation spectra for robust speech recognition

Yu Chen Kao, Berlin Chen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Modulation spectrum processing of speech features has recently become an active area of intensive research in the speech recognition community. As for normalization of modulation spectra, spectral histogram equalization (SHE) seems to be one of the most effective techniques that have been used to compensate the nonlinear distortion. In this paper, we investigate a novel use of polynomial-fitting techniques for modulation histogram equalization, which has the advantages of lower storage and time consumption when compared with the conventional SHE methods. Further, we also investigated the possibility of combining our approach with other temporal feature normalization methods. The automatic speech recognition (ASR) experiments were carried out on the Aurora-2 standard noise-robust ASR task. The performance of the proposed approach was thoroughly tested and verified by comparisons with the other popular modulation spectrum normalization methods, which suggests the utility of the proposed approach.

Original languageEnglish
Title of host publication2012 11th International Conference on Information Science, Signal Processing and their Applications, ISSPA 2012
Pages120-125
Number of pages6
DOIs
Publication statusPublished - 2012 Nov 12
Event2012 11th International Conference on Information Science, Signal Processing and their Applications, ISSPA 2012 - Montreal, QC, Canada
Duration: 2012 Jul 22012 Jul 5

Publication series

Name2012 11th International Conference on Information Science, Signal Processing and their Applications, ISSPA 2012

Other

Other2012 11th International Conference on Information Science, Signal Processing and their Applications, ISSPA 2012
CountryCanada
CityMontreal, QC
Period12/7/212/7/5

    Fingerprint

Keywords

  • modulation spectrum
  • robust speech recognition
  • spectral histogram equalization
  • temporal average

ASJC Scopus subject areas

  • Computer Science Applications
  • Signal Processing

Cite this

Kao, Y. C., & Chen, B. (2012). Leveraging distributional characteristics of modulation spectra for robust speech recognition. In 2012 11th International Conference on Information Science, Signal Processing and their Applications, ISSPA 2012 (pp. 120-125). [6310476] (2012 11th International Conference on Information Science, Signal Processing and their Applications, ISSPA 2012). https://doi.org/10.1109/ISSPA.2012.6310476