Monaural Speech Separation Method Based on CASA
WANG Kailong
ZHANG Erhua
CAO Guanbin
Abstract：Based on the auditory characteristics of the human ear,combined with the distribution characteristics of the spec?trum of the speech signal,a complete set of signal separation method is established. Firstly,the pitch period of each speech frame is extracted accurately by using the method of map analysis. Then,the speaker's spectrum template is constructed based on this,the original spectrum is filtered by comb filter with appropriate window function,and the separated speech is obtained by inverse Fouri?er transform. The experimental results show that the method is effective.
Keywords：CASAmonauralspeech separationpitch
Publication Date：2019-01-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：6( 1049-1054 )