Loading...

Robust speech recognition using MLP neural network in log-spectral domain

Ghaemmaghami, M. P ; Sharif University of Technology

890 Viewed
  1. Type of Document: Article
  2. DOI: 10.1109/ISSPIT.2009.5407513
  3. Abstract:
  4. In this paper, we have proposed an efficient and effective nonlinear feature domain noise suppression algorithm, motivated by the minimum mean square error (MMSE) optimization criterion. A Multi Layer Perceptron (MLP) neural network in the log spectral domain has been employed to minimize the difference between noisy and clean speech. By using this method, as a pre-processing stage of a speech recognition system, the recognition rate in noisy environments has been improved. We extended the application ofthe system to different environments with different noises without retraining HMMmodel. We trained the feature extraction stage with a small portion of noisy data which was created by artificially adding different types ofnoises from the NOISEX-92 database to the TIMIT speech database. In real environment, where our speech recognition systems must work, different types ofnoises with various SNRs exist. Our proposed method suggests four strategies based on the system capability to identify the noise type and SNR. Experimental results show that the proposed method achieves significant improvement in recognition rates. ©2009 IEEE
  5. Keywords:
  6. Log spectral ; MLP neural network ; Clean speech ; Log-spectral domain ; Minimum mean-square error ; MLP neural networks ; Multi layer perceptron ; Noise suppression algorithm ; Noise types ; Noisy data ; Noisy environment ; Nonlinear features ; Optimization criteria ; Pre-processing ; Real environments ; Recognition rates ; Robust speech recognition ; Speech database ; Speech recognition systems ; System capabilities ; Feature extraction ; Information technology ; Neural networks ; Optimization ; Signal processing ; Strain measurement ; Speech recognition
  7. Source: IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2009, 14 December 2009 through 16 December 2009, Ajman ; 2009 , Pages 467-472 ; 9781424459506 (ISBN)
  8. URL: http://ieeexplore.ieee.org/document/5407513