| 摘要 |
<p><P>PROBLEM TO BE SOLVED: To provide a technique which is capable of suppressing degradation of a target voice to record the target voice while removing or reducing unnecessary sounds and of efficiently providing information desired by a user. <P>SOLUTION: A voice recording server device (20) includes: a voice signal processing unit (27) which processes a first sound signal representing a voice of a speaker on the basis of a second sound signal representing sounds other than the voice of the speaker to generate a processed sound signal where sound signal components included in the first sound signal and caused by sounds other than the voice of the speaker are removed or reduced; a dividing unit (102) which divides the processed sound signal to sound blocks; acquisition means (104) which acquires a keyword registered for a specific user, from a database (29) where keywords registered for a plurality of users respectively are stored; extraction means (105) which extracts sound blocks including the acquired keyword; and combining means (106) which combines the extracted sound blocks to generate a reconfigured sound signal. <P>COPYRIGHT: (C)2013,JPO&INPIT</p> |
