| 摘要 |
<P>PROBLEM TO BE SOLVED: To provide an acoustic signal processing apparatus, method and program and recording medium with the acoustic signal processing program recorded thereon, for sound source normalization and sound source isolation, capable of dealing with sound sources as many as or more than the number of microphones, while relaxing the limitations on the sound sources. <P>SOLUTION: Two pieces of amplitude data of microphones 1a and 1b, inputted to an acoustic signal input unit 2, are analyzed by a frequency analysis unit 3, and the phase difference between the both is determined for each frequency by a two-dimensional data forming unit 4. The phase difference for each frequency is made into two-dimensional data by giving two-dimensional coordinate values thereto. A graphic detection unit 5 detects a graphic, by analyzing generated two-dimensional data on an XY plane. A sound source information generating unit 6 processes information on the detected graphic and generates sound source information, containing the number of sound sources as acoustic signal generating sources, spatial existence range of sound sources, temporal existence period of time of sound generated by the sound sources, component constitution of sound source sounds, isolated sounds for each sound source, and symbolic contents of the sound-source sounds. <P>COPYRIGHT: (C)2006,JPO&NCIPI |
