Sound source separating device, speech recognizing device, portable telephone, and sound source separating method, and program
作者： Shinya Matsui , Katsumasa Nagahama
DOI:
关键词:
摘要: The sound source signal from a target is separated the mixed in which signals sources are without being influenced by variations of sensitivity microphone elements. A beam former section (3) separating device (1) performs formation to attenuate arriving directions symmetrical with respect vertical line connecting two microphones (10, 11) spectrum-analyzing output and multiplying after spectrum analysis weighting factors complex conjugated signals. Power calculating sections (40, 41) calculate power information. Target extracting (50, 51) extract information on according difference between one that other.
lens.org 参考文章(3)
I.A. McCowan, S. Sridharan, Adaptive parameter compensation for robust hands-free speech recognition using a dual beamforming microphone array international symposium on intelligent multimedia video and speech processing. pp. 547- 550 ,(2001) , 10.1109/ISIMP.2001.925454
丈郎 金森, Tomomi Matsuoka, Takeo Kanamori, Takeshi Kawamura, 智美 松岡, 岳 河村, Microphone unit and reproducing apparatus ,(2003)
Hitoshi Nagata, 博史 金澤, Hiroshi Kanazawa, 仁史 永田, Ko Amada, 皇 天田, Method of processing sound signal, and system and program therefor ,(2003)