• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to project page

1999 Fiscal Year Final Research Report Summary

Robust HMMs against environmental variation for speech recognition

Research Project

Project/Area Number 10680376
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeSingle-year Grants
Section一般
Research Field Intelligent informatics
Research InstitutionShinshu University

Principal Investigator

MATSUMOTO Hiroshi  Fac. of Engineering, Shinshu University, Professor, 工学部, 教授 (60005452)

Project Period (FY) 1998 – 1999
KeywordsVariance expansion / Noise HMM / Noisy speech recognition / HMM composition / Noise robustness
Research Abstract

(1) A Study on Variance Expansion of HMMs Robust to Environmental Variation
This project addresses the problem of making HMMs robust to variation of SNR. This study developed a noise varicance expansion technique for HMMs, which consists of simply expanding the variace of cepstral coefficients for the noise model in HMM composition. The effect of this technique is examined through speaker independent digit recognition tests using NOISEX-92 noise data. The results show that the variance expansion of the 0th order cepstrum extremely improves robustness to a wide range of SNR mismatch over the standard HMM. The appropriate expansion factor is determined irrespective of noise types such that the expanded variance of the zeroth cepstrum is around 5 to 6dB with respect to its geometric mean.
(2) A Stuty on a Robust Spectral Analysis to Additive Noise
A part of this project also developed a simple and efficient time domain technique to estimate an all-poll model on a mel-frequency axis (Mel-LPC). This method requires only two-fold computational cost as compared to conventional linear prediction analysis. Gender-dependent phoneme recognition tests show that the Mel-LPC cepstrum attains a significant improvement in recognition accuracy over conventional LP mel-cepstra and the mel-frequency cepstrum coefficients (MFCC). Furthermore, noisy word recognition tests revealed that the Mel-LPC cepstrum is robust to wide-band additive noise over conventional LP mel-cepstrum and MFCC.

  • Research Products

    (4 results)

All Other

All Publications (4 results)

  • [Publications] H.Matsumoto, et al: "An efficient Mel-LPC analysis method for speech recognition"Proc. of International Conference on Spoken Language Processing. 1051-1054 (1998)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] H.Matsumoto, et al: "Robust HMM to variation of noisy environments based on variance extension of noise models"Proc. of 6th European Speech Conference. 2387-2390 (1999)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] H. Matsumoto, et al.: "An efficient Mel-LPC analysis method for speech recognition"Proc. of ICSLP'98. 1051-1054 (1998)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] H. Matsumoto, et al.: "Robust HMM to variation of noisy environments based on variance extension of noise models"Proc. of 6th ESCA. 2387-2390 (1999)

    • Description
      「研究成果報告書概要(欧文)」より

URL: 

Published: 2001-10-23  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi