DocumentCode
1635403
Title
A neural network approach to formant estimation
Author
Zhu, X.-Y. ; Cahill, L.W.
Author_Institution
Dept. of Electron Eng., La Trobe Univ., Bundoora, Vic., Australia
fYear
1992
Firstpage
540
Abstract
A neural network with two hidden layers is designed to estimate formant frequencies from linear predictive coding (LPC) coefficients. The formant estimation model reflects the nonlinear relationship between formants and LPC coefficients. Experiments of formant estimation on vowels and diphthongs are described and discussed. The results indicate that the neural network approach is a reliable formant estimation method
Keywords
linear predictive coding; neural nets; speech recognition; diphthongs; formant estimation; hidden layers; linear predictive coding; neural network; vowels; Artificial neural networks; Cepstral analysis; Design engineering; Electrodes; Frequency estimation; Linear predictive coding; Marine vehicles; Neural networks; Resonance; Speech;
fLanguage
English
Publisher
ieee
Conference_Titel
TENCON '92. ''Technology Enabling Tomorrow : Computers, Communications and Automation towards the 21st Century.' 1992 IEEE Region 10 International Conference.
Conference_Location
Melbourne, Vic.
Print_ISBN
0-7803-0849-2
Type
conf
DOI
10.1109/TENCON.1992.272007
Filename
272007
Link To Document