DocumentCode :
460417
Title :
A LSA-MMSE Speech Enhancement Approach Incorporating Masking Properties
Author :
Chen, Qi ; Guo, Ying ; Duan, Yanli ; Wang, Bo
Author_Institution :
Telecommun. Eng. Inst., AFEU, Xi´´an
Volume :
1
fYear :
2006
fDate :
25-28 June 2006
Firstpage :
455
Lastpage :
458
Abstract :
To improve the effect of single channel speech enhancement at low signal-to-noise ratio (SNR), this paper proposed a optimal speech enhancement scheme. Based on auditory masking effects, the speech spectra estimation is performed in two cases: noisy speech spectra for noise masked and classical spectral subtraction estimate for noise unmasked. Then a speech signal estimator is proposed as a weighted sum of the individual estimator in each state. Compared with Virag´s method and LSA-MMSE estimator, the proposed estimator can suppress the residual noise effectively while keep smaller speech distortion especially at low SNR
Keywords :
hearing; least mean squares methods; speech enhancement; speech intelligibility; LSA-MMSE speech enhancement; auditory masking effects; noisy speech spectra estimation; Acoustic noise; Amplitude estimation; Masking threshold; Noise level; Noise reduction; Phase noise; Signal to noise ratio; Speech coding; Speech enhancement; State estimation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Communications, Circuits and Systems Proceedings, 2006 International Conference on
Conference_Location :
Guilin
Print_ISBN :
0-7803-9584-0
Electronic_ISBN :
0-7803-9585-9
Type :
conf
DOI :
10.1109/ICCCAS.2006.284675
Filename :
4063919
Link To Document :
بازگشت