Optimization of TESPAR Features using Robust F-Ratio for Speaker Recognition

Author

Prasad, K. Satya ; Sheela, K. Anitha ; Sridevi, M.

Author_Institution

DSP Group, Jawaharlal Nehru Technol. Univ., Hyderabad

fYear

2007

fDate

22-24 Feb. 2007

Firstpage

20

Lastpage

25

Abstract

This paper deals with implementing an efficient optimization technique for designing an automatic speaker recognition (ASR) System, which uses average F-ratio score of TESPAR features, to yield high recognition accuracy even in adverse noisy conditions. A new ranking scheme is also proposed in order to stabilize the rank of features in various noise levels by taking arithmetic mean of the F-Ratio scores obtained from various levels of signal to noise ratio (SNR). The result is presented for a text-dependent ASR system with 20 speaker database. An RBF (radial basis function) neural network is used for recognition purpose

Keywords

radial basis function networks; speaker recognition; ASR system; RBF neural network; TESPAR feature; automatic speaker recognition; radial basis function; robust F-ratio; Automatic speech recognition; Design optimization; Frequency domain analysis; Loudspeakers; Neural networks; Noise level; Noise robustness; Signal to noise ratio; Spatial databases; Speaker recognition; ASR; Average F-Ratio; F-Ratio; RBF Neural Network; TESPAR;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing, Communications and Networking, 2007. ICSCN '07. International Conference on

Conference_Location

Chennai

Print_ISBN

1-4244-0997-7

Electronic_ISBN

1-4244-0997-7

Type

conf

DOI

10.1109/ICSCN.2007.350673

Filename

4156576