DocumentCode :
241268
Title :
Enhanced forensic multiple speaker recognition in the presence of coloured noise
Author :
Denk, Florian ; da Costa, Joao Paulo C. L. ; Almeida Silveira, Matheus
Author_Institution :
Dept. of Electr. Eng., Univ. of Brasilia, Brasilia, Brazil
fYear :
2014
fDate :
15-17 Dec. 2014
Firstpage :
1
Lastpage :
7
Abstract :
Automatic speaker recognition has become a well-established technique for forensic applications. Since ambient recordings in such applications are obtained with hidden microphones far away from the sound sources, the performance of the speaker recognition can be severely degraded. In this paper, we propose an array signal processing method to compensate for these disturbances by spatially separating the present individual speakers and noise using convolutive Independent Component Analysis and applying a noise-suppression method based on spectral subtraction to the separated sound signals. A speaker recognition scheme based on Mel-Frequency Cepstral Coefficients and Gaussian Mixture Models is then applied to the separated and noise-cancelled signals. Our proposed pre-processing method dramatically increases the reliability of speaker recognition under such aggravated conditions and outperforms state-of-the-art solutions.
Keywords :
Gaussian processes; array signal processing; convolution; digital forensics; independent component analysis; mixture models; signal denoising; source separation; speaker recognition; Gaussian mixture models; Mel-frequency cepstral coefficients; array signal processing method; automatic speaker recognition; coloured noise; convolutive independent component analysis; disturbance compensation; enhanced forensic multiple speaker recognition scheme; hidden microphones; noise-cancelled signals; noise-suppression method; sound signal separation; sound sources; speaker recognition reliability; spectral subtraction; Feature extraction; Mel frequency cepstral coefficient; Noise cancellation; Signal to noise ratio; Speaker recognition; Speech;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Signal Processing and Communication Systems (ICSPCS), 2014 8th International Conference on
Conference_Location :
Gold Coast, QLD
Type :
conf
DOI :
10.1109/ICSPCS.2014.7021056
Filename :
7021056
Link To Document :
بازگشت