Loading...

The combination of CMS with PMC for improving robustness of speech recognition systems

Veisi, H ; Sharif University of Technology | 2008

239 Viewed
  1. Type of Document: Article
  2. DOI: 10.1007/978-3-540-89985-3_112
  3. Publisher: 2008
  4. Abstract:
  5. This paper addresses the robustness problem of automatic speech recognition systems for real applications in presence of noise. PMCC algorithm is proposed for combining PMC technique with CMS method. The proposed algorithm utilizes the CMS normalization ability in PMC method to takes the advantages of these methods to compensate the effect of both additive and convolutional noises. Also, we have investigated VTLN for speaker normalization and MLLR and MAP for speaker and acoustic adaptation. Different combinations of these methods are used to achieve robustness and making the system usable in real applications. Our evaluations are done on 4 different real noisy tasks on Nevisa recognition system. Experimental results show the effectiveness of proposed method and significant improvement in system performance. © 2008 Springer-Verlag
  6. Keywords:
  7. Acoustic adaptation ; Automatic speech recognition system ; Cepstral mean subtraction ; Parallel model combinations ; Real applications ; Recognition systems ; Robustness ; Speaker normalization ; Speech recognition systems ; Computer science ; Convolution ; Speech recognition
  8. Source: 13th International Computer Society of Iran Computer Conference on Advances in Computer Science and Engineering, CSICC 2008, Kish Island, 9 March 2008 through 11 March 2008 ; Volume 6 CCIS , 2008 , Pages 825-829 ; 18650929 (ISSN); 3540899847 (ISBN); 9783540899846 (ISBN)
  9. URL: https://link.springer.com/chapter/10.1007%2F978-3-540-89985-3_112