Speech enhancement method
作者： Hsien Cheng Liao
DOI:
关键词:
摘要: A speech enhancement method is disclosed. The includes the steps of: receiving a plurality of frames sound signals by microphone array; calculating an inter-aural time difference for each frequency band frame corresponding to at least one two-microphone set values cumulative histograms according calculated differences; determining first threshold value histograms; and filtering threshold.
lens.org 参考文章(6)
Martin Bouchard, Homayoun Kamkar Parsi, Method and system for a multi-microphone noise reduction ,(2010)
Alan Lawrence Higgins, Jack E. Porter, Steven F. Boll, Noise suppression and channel equalization preprocessor for speech and speaker recognizers: method and apparatus ,(1998)
Hyun Jin Park, Erik Visser, Jeremy Toman, Kwok-Leung Chan, Systems, methods, and apparatus for multi-microphone based speech enhancement ,(2008)
Tomohiro Nakatani, Hiroshi G. Okuno, Harmonic sound stream segregation using localization and its application to speech stream segregation Speech Communication. ,vol. 27, pp. 209- 222 ,(1999) , 10.1016/S0167-6393(98)00079-X
Milan Jelinek, Method and device for speech enhancement in the presence of background noise ,(2004)
Kaoru Koga Toshiyuki Suzuki, Acoustic signal processing apparatus and processing method thereof ,(2006)