DocumentCode :
3239934
Title :
Improved Spectral Subtraction Technique for Text-Independent Speaker Verification
Author :
Panda, Ashish ; Tripathi, Neha ; Srikanthan, Thambipillai
Author_Institution :
Nanyang Technol. Univ., Singapore
fYear :
2007
fDate :
1-4 July 2007
Firstpage :
595
Lastpage :
598
Abstract :
The presence of different types of noise during enrollment and verification phase results in severe performance degradation in speaker verification systems. Spectral subtraction is a speech enhancement method which is often used to estimate the clean speech. However, spectral subtraction loses its accuracy in the frames with low signal-to-noise-ratio. In this paper, we present a variance measure for the low signal-to- noise-ratio frames which reflects the effectiveness of the estimate given by the spectral subtraction. This variance measure is then used to calculate the expected value of the log- likelihood score during the verification phase. Our experiments with various types of noise shows that the proposed method improves the performance of the spectral subtraction method by up to 23%.
Keywords :
speaker recognition; spectral analysis; speech enhancement; log-likelihood score; low signal-to-noise-ratio frames; noise; spectral subtraction technique; speech enhancement method; text-independent speaker verification; variance measure; Additive noise; Background noise; Degradation; Embedded system; Frequency estimation; Hidden Markov models; Phase noise; Random variables; Speech enhancement; Subtraction techniques; Noise; Speaker Verification; Spectral Subtration;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Digital Signal Processing, 2007 15th International Conference on
Conference_Location :
Cardiff
Print_ISBN :
1-4244-0881-4
Electronic_ISBN :
1-4244-0882-2
Type :
conf
DOI :
10.1109/ICDSP.2007.4288652
Filename :
4288652
Link To Document :
بازگشت