Title :
Complex cepstrum based single channel speech dereverberation
Author :
Xizhong, Shen ; Guang, Meng
Author_Institution :
Mech. & Electr. Dept., Shanghai Inst. of Technol., Shanghai, China
Abstract :
A new method of blind dereverberation of single channel is proposed to solve the existing problem about the study of speech signal. Firstly, segmentation of speech signal with variant length is proposed on the sampled speech signal to obtain relatively accurate estimation of the subsequent cepstrum, and the complex cepstrum is applied to the valid segments. Then, the pre-estimation of the room impulse response is obtained, and so is the inverse-filter solution. Finally, single channel blind deconvolution is used by taking the inverse-filter as the initial parameter of the algorithm. Simulations and experiments demonstrate its validity and robusty.
Keywords :
acoustic filters; blind source separation; cepstral analysis; deconvolution; speech processing; blind dereverberation; complex cepstrum; inverse-filter; inverse-filter solution; room impulse response; single channel dereverberation; speech dereverberation; speech signal segmentation; Automatic speech recognition; Cepstrum; Computer science; Computer science education; Deconvolution; Educational technology; Laboratories; Microphones; Reverberation; Robustness; Complex cepstrum; Dereverberation; Room Impulse response; Segmentation; Speech;
Conference_Titel :
Computer Science & Education, 2009. ICCSE '09. 4th International Conference on
Conference_Location :
Nanning
Print_ISBN :
978-1-4244-3520-3
Electronic_ISBN :
978-1-4244-3521-0
DOI :
10.1109/ICCSE.2009.5228535