专利名称:METHOD AND SYSTEM FOR SEPARATING
PLURALITY OF ACOUSTIC SIGNALSGENERATED BY PLURALITY OF ACOUSTICSOURCES
发明人:RAMAKRISHNAN, Bhiksha,GOMEZ, Manuel, J.
Reyes
申请号:EP03789598.4申请日:20031211公开号:EP1568013A1公开日:20050831
摘要:A method separates acoustic signals generated by multiple acoustic sources,such as mixed speech spoken simultaneously by several speakers in the same room. Foreach source, the acoustic signals are combined into a mixed signal acquired by multiplemicrophones, at least one for each source. The mixed signal is filtered, and the filteredsignals are summed into a signal from which features are extracted. A target sequencethrough a factorial HMM is estimated, and filter parameters are optimized accordingly.These steps are repeated until the filter parameters converge to optimal filteringparameters, which are then used to filter the mixed signal once more, and the summedoutput of this last filtering is the acoustic signal for a particular acoustic source.
申请人:MITSUBISHI DENKI KABUSHIKI KAISHA
地址:2-3, Marunouchi 2-chome, Chiyoda-ku Tokyo 100-8310 JP
国籍:JP
代理机构:Gleiter, Hermann
更多信息请下载全文后查看
因篇幅问题不能全部显示,请点此查看更多更全内容