VOIP compressed-domain automatic speaker recognition based on probabilistic stochastic histogram

Author

Dan, Qu ; Honggang, Yan ; Hui, Tang ; Bingxi, Wang

Author_Institution

Zhengzhou Inf. Sci. & Techonology Inst., Zhengzhou

fYear

2008

Firstpage

692

Lastpage

696

Abstract

Compressed-domain automatic speaker recognition is based on the analysis of the compressed parameters of speech coders. This paper presents compressed-domain speaker recognition approach based on the Probabilistic Stochastic Histogram algorithm. We propose a framework based on Vector Quantization Probabilistic Stochastic Histogram(VQPSH) algorithm and perform speaker recognition on the feature vector which is directly extracted from G.729, G.723.1 6.3k, G723.1 5.3k compressed bit stream. We also propose a speaker recognition algorithm based on Gaussian Mixture Model Probabilistic Stochastic Histogram (GMMPSH). The experimental results show the Probabilistic Stochastic Histogram is superior to classical GMM using the same feature vector.

Keywords

Gaussian processes; Internet telephony; probability; speaker recognition; vector quantisation; VOIP compressed-domain; automatic speaker recognition; gaussian mixture model; probabilistic stochastic histogram; speech coders; vector quantization; Automatic speech recognition; Decoding; Feature extraction; Histograms; IP networks; Internet telephony; Speaker recognition; Speech analysis; Stochastic processes; Vector quantization;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing, 2008. ICSP 2008. 9th International Conference on

Conference_Location

Beijing

Print_ISBN

978-1-4244-2178-7

Electronic_ISBN

978-1-4244-2179-4

Type

conf

DOI

10.1109/ICOSP.2008.4697225

Filename

4697225