Loading...

The effect of phase information in speech enhancement and speech recognition

Langarani, M. S. E ; Sharif University of Technology | 2012

561 Viewed
  1. Type of Document: Article
  2. DOI: 10.1109/ISSPA.2012.6310533
  3. Publisher: 2012
  4. Abstract:
  5. The majority of speech enhancement methods perform noise removal in spectral domain and construct the enhanced speech signal from the estimated magnitude of clean speech and the phase of the noisy speech. In this paper, we show that by incorporating the phase information in the enhancement process, the quality and intelligibility of speech signal are improved. In our investigations, the minimum mean-square error short-time spectral amplitude and MMSE log-spectral amplitude methods are used to estimate the magnitude spectrum of speech signal. By conducting six classes of experiments, it is shown that by taking the phase information into account, overall SNR and PESQ measures are improved. In other experiments, the results of speech enhancement system are fed into a speech recognition system and it is shown that by incorporating accurate phase information, the intelligibility of the speech signal is improved
  6. Keywords:
  7. Clean speech ; Magnitude spectrum ; Minimum mean-square error ; Noise removal ; Noisy speech ; Phase information ; Spectral amplitude ; Spectral domains ; Speech enhancement methods ; Speech enhancement system ; Speech recognition systems ; Speech signals ; Experiments ; Information science ; Signal processing ; Signal to noise ratio ; Speech enhancement ; Speech recognition
  8. Source: 2012 11th International Conference on Information Science, Signal Processing and their Applications, ISSPA 2012, 2 July 2012 through 5 July 2012 ; 2012 , Pages 1446-1447 ; 9781467303828 (ISBN)
  9. URL: http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6310533