Loading...

A comparative study on single-channel noise estimation methods for speech enhancement

Veisi, H ; Sharif University of Technology | 2012

774 Viewed
  1. Type of Document: Article
  2. DOI: 10.1109/ISDA.2012.6416613
  3. Publisher: 2012
  4. Abstract:
  5. This paper studies a number of well-known noise estimation techniques and provides a comparative performance analysis of them in speech enhancement platform. Two types of evaluation data that simulate consistent and inconsistent noisy conditions are prepared in the presence of six noise types at different SNR levels. The performance of speech enhancement systems and the spectrum distance of the estimated and original noise spectrums are used as evaluation criteria. The evaluations indicate that a simple VAD method outperforms noise estimation methods in most of the consistent noisy conditions
  6. Keywords:
  7. Minimal tracking ; Comparative performance analysis ; Comparative studies ; Evaluation criteria ; Minimum controlled recursive average ; Noise estimation ; Noise spectrum ; Noise types ; Noisy conditions ; Single-channel ; Speech enhancement system ; VAD ; Intelligent systems ; Signal to noise ratio ; Systems analysis ; Speech enhancement
  8. Source: International Conference on Intelligent Systems Design and Applications, ISDA ; 2012 , Pages 645-650 ; 21647143 (ISSN) ; 9781467351188 (ISBN)
  9. URL: http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6416613