| 摘要 |
<P>PROBLEM TO BE SOLVED: To provide a technique enabling a user to easily input a voice of musical interval as intended, into a retrieval device for retrieving a musical piece based on the inputted voice. <P>SOLUTION: When the user sings, the user's singing voice is picked up by a microphone 15 and converted into voice signals. A control part 11 of a Karaoke (sing-along music) device 1 detects pitches from the inputted voice signals, and normalizes the detected pitches in halftone or whole tone pitches. The control part 11 detects a pause of notes of the voice signals based on sound pressure of the voice signals and specifies representative values of the pitches for every note. The control part 11 then generates MIDI data from the specified representative values for every note and supplies it to a voice processing part 16. The voice processing part 16 generates musical sound signals from the supplied MIDI data and outputs them as musical sounds from a loudspeaker 17. <P>COPYRIGHT: (C)2009,JPO&INPIT |
