Abstract:
Many applications of speech communication and speaker identification suffer from the problem of co-channel speech. This paper deals with a multi-resolution analysis by em...Show MoreMetadata
Abstract:
Many applications of speech communication and speaker identification suffer from the problem of co-channel speech. This paper deals with a multi-resolution analysis by empirical mode decomposition for usable speech segments detection of co-channel speech. Usable speech detected could be processed by a speaker identification system. Experiment and evaluation of this method is performed on TIMIT database.
Date of Conference: 18-21 March 2013
Date Added to IEEE Xplore: 22 July 2013
ISBN Information: