Design and Implementation of a Real-Time Speaker Identification System with Improved GMM

Author

Jiang, Ye ; Tang, Zhen-min

Author_Institution

Sch. of Comput. Sci. & Technol., Nanjing Univ. of Sci. & Technol., Nanjing, China

fYear

2009

fDate

4-6 Nov. 2009

Firstpage

1

Lastpage

5

Abstract

The text-independent real-time speaker identification system is presented. It is based on Gaussian Mixture Model and MFCC (Mel frequency cepstral coefficients) method to extract the character of speech signal. The traditional method of GMM parameters initialization includes random method and k-means clustering are lack of clustering accuracy. A new approach which combines division and k-means clustering is presented and applied to the system. The system is realized under windows platform with good face. It includes voice collection and storage, speech pre-processing, MFCC extraction, GMM training and storage, speaker identification and so on. The experiment shows that the improved method as compared with the traditional method, the system average recognition rate has an increase of 18.34% and 7.98%. The system can achieve the error rate with 6.7% under the provided experimental condition.

Keywords

Gaussian processes; pattern clustering; speaker recognition; GMM; Gaussian mixture model; MFCC extraction; MFCC method; Mel frequency cepstral coefficients; character extraction; k-means clustering; random method; speech pre-processing; speech signal; text-independent real-time speaker identification system; voice collection; voice storage; Artificial neural networks; Computer science; Error analysis; Mel frequency cepstral coefficient; Real time systems; Speaker recognition; Speech; Vector quantization;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 2009. CCPR 2009. Chinese Conference on

Conference_Location

Nanjing

Print_ISBN

978-1-4244-4199-0

Type

conf

DOI

10.1109/CCPR.2009.5344040

Filename

5344040