DocumentCode
2041840
Title
A combined neural network and hidden Markov model approach to speaker recognition
Author
Xiao-Yuan Zhu
Author_Institution
Dept. of Electron. Eng., La Trobe Univ., Bundoora, Vic., Australia
Volume
2
fYear
1993
fDate
19-21 Oct. 1993
Firstpage
1074
Abstract
Presents a combination approach to text-independent speaker identification. The approach makes use of the strong classification power of an artificial neural network and the hidden Markov model´s ability to handle the sequential character of speech. The combination approach is superior to both the neural network approach and the hidden Markov model approach in identification accuracy and computational complexity.<>
Keywords
biometrics (access control); computational complexity; hidden Markov models; neural nets; speech recognition; artificial neural network; classification; computational complexity; hidden Markov model; identification accuracy; sequential characteristics; speaker recognition; text-independent speaker identification; Artificial neural networks; Hidden Markov models; Neural networks; Power engineering and energy; Signal processing; Speaker recognition; Speech processing; Speech recognition; Testing; Viterbi algorithm;
fLanguage
English
Publisher
ieee
Conference_Titel
TENCON '93. Proceedings. Computer, Communication, Control and Power Engineering.1993 IEEE Region 10 Conference on
Conference_Location
Beijing, China
Print_ISBN
0-7803-1233-3
Type
conf
DOI
10.1109/TENCON.1993.320201
Filename
320201
Link To Document