Presentation 1993/12/14
Learning of Speech Waveforms Using Recurrent Neural Networks
Shozo Sato, Hiroaki Kuno, Kazutoshi Gouhara,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We show experimentally that RNN(Recurrent Neural Networks)can learn complex speech waveforms with a few thousand steps of length using the proposed reaning method.After sufficient reaning, attractors corresponding to desired transformation of input-output patterns were formed in the state space.Increasing the number of reaning patterns,desired responses are obtained for unleaning patterns.We propose a new method of speech recognition by reaning speech waveforms.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Recurrent Neural Networks / Supervised Learning / Attractor / Speech Waveform / Speech Recognition
Paper # NC93-56
Date of Issue

Conference Information
Committee NC
Conference Date 1993/12/14(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Learning of Speech Waveforms Using Recurrent Neural Networks
Sub Title (in English)
Keyword(1) Recurrent Neural Networks
Keyword(2) Supervised Learning
Keyword(3) Attractor
Keyword(4) Speech Waveform
Keyword(5) Speech Recognition
1st Author's Name Shozo Sato
1st Author's Affiliation Department of Electrical Engineering,School of Engineering,Chubu University()
2nd Author's Name Hiroaki Kuno
2nd Author's Affiliation Department of Electrical Engineering,School of Engineering,Chubu University
3rd Author's Name Kazutoshi Gouhara
3rd Author's Affiliation Department of Electrical Engineering,School of Engineering,Chubu University
Date 1993/12/14
Paper # NC93-56
Volume (vol) vol.93
Number (no) 376
Page pp.pp.-
#Pages 8
Date of Issue