发明名称 VOICE PROCESSING SYSTEM AND VOICE PROCESSING METHOD
摘要 PROBLEM TO BE SOLVED: To emphatically output voice data in video to arbitrary reproduction time during reproduction of recorded video data and voice data.SOLUTION: A recorder 45 accepts designation of video to be reproduced from a user. When a signal processing section 50 accepts designation of one or more designation portions of voice emphasis from a user via an operation section 55 to a screen of a display 63 where the video is displayed while the recorder 45 reproduces the video or during a halt, the signal processing section performs emphasis processing on voice data, namely, emphasizes the voice data in a direction to a position corresponding to the designated portion from a microphone array 20 by using the voice data recorded in the recorder 45. A reproducer 60 synchronizes the voice data and the video data, which are emphasis-processed, to reproduce them.
申请公布号 JP2014143678(A) 申请公布日期 2014.08.07
申请号 JP20130252468 申请日期 2013.12.05
申请人 PANASONIC CORP 发明人 SAWA HIROTAKA;SHIGENAGA SHINICHI;TOKUDA TADAMICHI;YOSHIKUNI SHINTARO;WATANABE SHUICHI;MAKI TADASHI;TASAKA KOICHI;ONO SUSUMU;FUJIMOTO KEISUKE;MATSUO SHOJIRO;FUKUDA TEPPEI;MATSUMOTO HIROYUKI;IZUMI AKITOSHI;TSUJI TOSHITSUGU;HAYASHI KAZUNORI;YUSHIMO RYOICHI
分类号 H04N5/225;G10L21/028;G11B20/10;H04N5/93;H04R1/02;H04R1/40;H04R3/00 主分类号 H04N5/225
代理机构 代理人
主权项
地址