Paper Info
Title
Speaker Verification System Using A Hierarchical Adaptive Network-Based Fuzzy Inference Systems (Hanfis)
Abstract
We propose the use of a hierarchical adaptive network-based fuzzy inference system (HANFIS) for automated speaker verification of Persian speakers from their English pronunciation of words. The proposed method uses three classes of sound properties consisting of linear prediction coefficients (LFC), word time- length, intensity and pitch, as well as frequency properties from FFT analysis. Actual audio data is collected from fourteen Persian speakers who spoke English. False acceptance ratio and false rejection ratio as are evaluated for various HANFIS trained with different radius. Results indicate that vowel sounds can be a good indicator for more accurate speaker verificatior.. Finally, the hierarchical architecture is shown to considerably improve performance than ANFIS.
Year
DOI
Venue
2010
10.1007/978-3-642-15286-3_23
ARTIFICIAL INTELLIGENCE IN THEORY AND PRACTICE III
Keywords
Field
DocType
ANFIS, Speaker verification, LPC, FFT, intensity and pitch coefficients, HANFIS
Speaker verification,Pronunciation,Pattern recognition,Computer science,Persian,Fuzzy inference,Speech recognition,Linear prediction,Fast Fourier transform,Artificial intelligence,Vowel,Adaptive neuro fuzzy inference system
Conference
Volume
ISSN
Citations 
331
1868-4238
0
PageRank 
References 
Authors
0.34
3
4
Name
Order
Citations
PageRank
Zohreh Soozanchi-K.100.34
Mohammad R. Akbarzadeh-Totonchi212518.26
Mahdi Yaghoobi3436.40
Saeed Rahati4503.73