DocumentCode :
730759
Title :
Phonological vocoding using artificial neural networks
Author :
Cernak, Milos ; Potard, Blaise ; Garner, Philip N.
Author_Institution :
Idiap Res. Inst., Martigny, Switzerland
fYear :
2015
fDate :
19-24 April 2015
Firstpage :
4844
Lastpage :
4848
Abstract :
We investigate a vocoder based on artificial neural networks using a phonological speech representation. Speech decomposition is based on the phonological encoders, realised as neural network classifiers, that are trained for a particular language. The speech reconstruction process involves using a Deep Neural Network (DNN) to map phonological features posteriors to speech parameters - line spectra and glottal signal parameters - followed by LPC resynthesis. This DNN is trained on a target voice without transcriptions, in a semi-supervised manner. Both encoder and decoder are based on neural networks and thus the vocoding is achieved using a simple fast forward pass. An experiment with French vocoding and a target male voice trained on 21 hour long audio book is presented. An application of the phonological vocoder to low bit rate speech coding is shown, where transmitted phonological posteriors are pruned and quantized. The vocoder with scalar quantization operates at 1 kbps, with potential for lower bit-rate.
Keywords :
neural nets; speech coding; DNN; LPC resynthesis; artificial neural networks; deep neural network; glottal signal parameters; line spectra; low bit rate speech coding; neural network classifiers; phonological features posteriors; phonological speech representation; phonological vocoding; speech decomposition; Digital audio players; Real-time systems; Parametric vocoding; low bit rate speech coding; phonology;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on
Conference_Location :
South Brisbane, QLD
Type :
conf
DOI :
10.1109/ICASSP.2015.7178891
Filename :
7178891
Link To Document :
بازگشت