Title :
Co-channel speech separation based on sinusoidal model for speech
Author :
Heming, Zhao ; Xudong, Zhou ; Yibiao, Yu
Author_Institution :
Dept. of Electron. Eng., Suzhou Univ., China
Abstract :
This paper proposed a sinusoidal model based cochannel speech separation method which is based on the assumption that a speech wave consists of a series of sinusoidal signals with time-varying amplitudes, frequencies and phases. In this paper subharmonic summation was expanded to overlapping speech situations to detect and separate the pitch frequencies of each speech. Then 2-D harmonic sieve arithmetic was proposed to obtain the harmonic frequencies, amplitudes and phases of each speech. Finally the components of each speech were separated by a sinusoidal model. This method is mainly suitable for overlapping vowels, and the experiment results showed it can effectively separate two overlapping speeches even when the pitch frequencies of the two speeches are relatively close
Keywords :
harmonic analysis; spectral analysis; speech processing; 2-D harmonic sieve arithmetic; co-channel speech separation; harmonic frequencies; overlapping speech; overlapping vowels; phase; pitch frequencies; sinusoidal model based cochannel speech separation; sinusoidal signals; speech wave; subharmonic summation; time-varying amplitude; Arithmetic; Frequency; Interference; Oral communication; Power harmonic filters; Signal synthesis; Speech coding; Speech processing; Speech synthesis; Statistics;
Conference_Titel :
Signal Processing Proceedings, 2000. WCCC-ICSP 2000. 5th International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-5747-7
DOI :
10.1109/ICOSP.2000.891636