| 摘要 |
<P>PROBLEM TO BE SOLVED: To optimize tradeoff between the possibility of the undesired alteration of the sound quality of a music and surrounding sounds and the benefit of a desired intelligibility. <P>SOLUTION: The voice of an entertainment audio is emphasized by a process of processing an entertainment audio in response to one or more control (signals) in order to improve the articulation and intelligibility of the voice section of the entertainment audio and a process of generating control for the processing. The process of generating control includes: a process of characterizing the temporal fragments of the entertainment audio as (a) voice or non-voice, or (b) being likely to be a voice or being likely to be a non-voice; and a process of responding to the level of the entertainment audio in order to provide control for the processing. <P>COPYRIGHT: (C)2013,JPO&INPIT |
