Two-stage blind source separation based on ICA and binary masking for real-time robot audition system
作者： H. Saruwatari , Y. Mori , T. Takatani , S. Ukai , K. Shikano
DOI: 10.1109/IROS.2005.1544983
关键词: Independent component analysis 、 Blind signal separation 、 Robot audition 、 Monaural 、 Speech recognition 、 Artificial intelligence 、 Masking (art) 、 Pattern recognition 、 Engineering 、 Binaural recording 、 Binary number 、 Humanoid robot
摘要: … masking effect which tells that the stronger signal masks the weaker one. We estimate a binary mask … is dominant and mask the other regions. Under the assumption that the l-th sound …
sci-hub.se 参考文章(2)
Rajkishore Prasad, Hiroshi Saruwatari, Kiyohiro Shikano, Robots that can hear, understand and talk Advanced Robotics. ,vol. 18, pp. 533- 564 ,(2004) , 10.1163/156855304774195064
S. Boll, Suppression of acoustic noise in speech using spectral subtraction IEEE Transactions on Acoustics, Speech, and Signal Processing. ,vol. 27, pp. 113- 120 ,(1979) , 10.1109/TASSP.1979.1163209