Loading...

A parallel cepstral and spectral modeling for HMM-based speech enhancement

Veisi, H ; Sharif University of Technology | 2011

472 Viewed
  1. Type of Document: Article
  2. DOI: 10.1109/ICDSP.2011.6004927
  3. Publisher: 2011
  4. Abstract:
  5. An HMM-based speech enhancement in Mel-frequency domain is introduced and improved. It is shown that hidden Markov modeling in the Mel-frequency domain is beneficial due to its effective representation of the speech spectrum; however, speech enhancement in this domain requires an inversion from the Mel-frequency to the spectral domain which introduces distortion artifacts for spectrum estimation. To reduce the distortion effects of the inversion and employ the advantages of robustness modeling in the Mel-frequency domain, a parallel cepstral and spectral (PCS) modeling is proposed. In PCS, a concurrent modeling in both cepstral and spectral domains is performed. The performances of the speech enhancement system using Mel-frequency spectral (MFS) and Mel-frequency cepstral (MFC) features and using the PCS modeling are evaluated on various corrupting noise types with different SNR levels. The results confirm the superiority of the proposed methods particularly in dealing with non-stationary noises
  6. Keywords:
  7. Mel-frequency ; parallel cepstral and spectral modeling ; Statistical HMM-based speech enhancement ; Cepstral ; Concurrent modeling ; Distortion effects ; Hidden Markov modeling ; Mel-frequency ; Noise types ; Nonstationary noise ; Spectral domains ; Spectral modeling ; Spectrum estimation ; Speech enhancement system ; Speech spectra ; Digital signal processing ; Frequency domain analysis ; Spectrum analysis ; Speech enhancement ; Frequency estimation
  8. Source: 17th DSP 2011 International Conference on Digital Signal Processing, Proceedings, 6 July 2011 through 8 July 2011, Corfu ; 2011 ; 9781457702747 (ISBN)
  9. URL: http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6004927