Voice output extraction by signal separation
GAIL ERTEN, F. Salam · 2002
The ability to selectively enhance audio signals of interest while suppressing spurious ones is an essential prerequisite to widespread practical use of voice activated systems. Such audio signal discrimination allows for selective amplification of a single source of speech within a mixture of two or more signals, including noise and other speakers' voices. This paper will present the most recent improvements on the algorithms we are developing, which are derived through realistic modeling of signal mixing environments in tandem with the use of dynamic multidisciplinary adaptation methods. The underlying technologies used in the compiled voice output extractor (VOX) software can significantly facilitate the embedding of speech recognition into many environments.