发明名称 VOICE PROCESSING DEVICE, VOICE PROCESSING METHOD AND PROGRAM
摘要 PROBLEM TO BE SOLVED: To provide a technique capable of highly accurately reducing noise included in voice.SOLUTION: A voice processing device comprises: first acquisition means for acquiring a voice signal; first setting means for setting a reference period; second setting means for setting a plurality of comparison periods; first detection means for detecting a plurality of similar periods from among the plurality of comparison periods; second detection means for detecting a fundamental frequency; second acquisition means for acquiring a phase different between a voice signal of the fundamental frequency in the reference period and a voice signal of the fundamental frequency in the similar period; selection means for selecting two or more similar periods from among the plurality of similar periods on the basis of the phase difference in each of the similar periods acquired by the second acquisition means; creation means for creating a replacement signal on the basis of a voice signal in the reference period and voice signals in the similar periods selected by the selection means; and replace means for replacing the voice signal in the reference period with the replacement signal.SELECTED DRAWING: Figure 1
申请公布号 JP2016045457(A) 申请公布日期 2016.04.04
申请号 JP20140171660 申请日期 2014.08.26
申请人 CANON INC 发明人 KAJIMURA FUMIHIRO
分类号 G10L21/0224;G10L21/0208;H04N5/225;H04R3/00 主分类号 G10L21/0224
代理机构 代理人
主权项
地址
您可能感兴趣的专利