摘要 |
PROBLEM TO BE SOLVED: To provide a recording or reproducing device, capable of discriminating a music piece from sound which is composed of the music piece and uttering voice, by simple arithmetic processing. SOLUTION: The device comprises: a cut point detection section for detecting a time point in which a change amount of a voice signal level is a predetermined value or more as the cut point; a frequency feature amount calculation section for calculating a feature amount in a frequency domain of the voice signal only near the cut point; a cut point determination section for determining an attribute of the cut point, based on the calculated frequency feature amount; and a music piece period detection section for detecting a start point and an end point of a music piece period, based on an interval between the attribute and a sampling point. COPYRIGHT: (C)2009,JPO&INPIT
|