On the Use of an Ear Model and Multi-Layered Networks for Automatic Speech Recognition

The paper describes a speech coding system based on an ear model followed by a set of Multi-Layer Networks (MLN). MLNs are trained to learn how to recognize articulatory features like the place and manner of articulation. Experiments are performed on 10 English vowels showing a recognition rate higher than 95% for new speakers. When features are used for recognition, comparable results are obtained for vowels and diphthongs not used for training and pronounced by new speakers. This suggests that MLNs suitably fed by the data computed by an ear model have good generalization capabilities over new speakers and new sounds.

Tipo Pubblicazione: 
Contributo in atti di convegno
Author or Creator: 
De Mori R.
Bengio Y.
Cosi P.
Publisher: 
World Scientific, Singapore, SGP
Source: 
Structural Pattern Analysis, Proceedings of the third SSPR (Syntactical and Structural Pattern Recognition) Workshop, pp. 37–56, Singapore, 1989
Date: 
1989
Resource Identifier: 
http://www.cnr.it/prodotto/i/241913
http://books.google.it/books?hl=it&lr=&id=fDTiqezgfDsC&oi=fnd&pg=PA37&dq=On+the+Use+of+an+Ear+Model+and+Multi-Layered+Networks+for+Automatic+Speech+Recognition&ots=M3MVILxbdz&sig=89Prx7yNR8K48baObsrWTmTgz8U#v=onepage&q=On%20the%20Use%20of%20an%20Ear%20Model%20and%20Multi-Layered%20Networks%20for%20Automatic%20Speech%20Recognition&f=false
urn:isbn:9810200978
Language: 
Eng
ISTC Author: 
Ritratto di Piero Cosi
Real name: