Signal processing system and method
作者： Takuya Noda , Kentaro Murase , Kazuhiro Watanabe
DOI:
关键词: Signal processing 、 Signal 、 Stationary noise 、 Pattern recognition 、 Electronic engineering 、 Artificial intelligence 、 Engineering 、 Section (archaeology)
摘要: An input signal is via an part. A plurality of section candidate detecting parts having different detection algorithms detect intended and a noise from the signal. classifying part notified results respective parts, classifies candidates based on combination results. The candidate, which detected as by all section, stationary any either non-stationary section.
lens.org 参考文章(8)
Yoshihisa Nakatoh, Takeshi Norimatsu, Method and an apparatus for speech detection for determining whether an input signal is speech or nonspeech ,(1994)
Takehiko Isaka, Yoshifumi Nagata, Method and apparatus for processing speech signals ,(2002)
Karl Torbjörn Wigren, Discriminating between stationary and non-stationary signals ,(1994)
Terrence J. Sejnowski, Michael S. Lewicki, Te-Won Lee, Unsupervised adaptation and classification of multiple classes and sources in blind signal separation ,(1999)
Shude Zhang, Method and apparatus for improved voice activity detection in a packet voice network ,(2001)
Robert A. Berkovitz, Nathaniel I. Durlach, Content analyzer mixing inverse-direction-probability-weighted noise to input signal ,(1995)
Carl J. May, Multiple variable threshold speech detector Journal of the Acoustical Society of America. ,vol. 78, pp. 285- 285 ,(1980) , 10.1121/1.392519
Leonid Krasny, Speech recognition using microphone antenna array Journal of the Acoustical Society of America. ,vol. 119, pp. 690- ,(2001) , 10.1121/1.2174515