A Sonn-Based Architecture for Automatic Speech Segmentation and Alignment

A Self-Organizing-Neural-Network(SONN) architecture is used, in cooperation with Viterbi decoding and One-Pass Level-Building(LB) tecnique for automatic alignment of incoming speech signals with their corresponding indipendently specified string of phonetic/phonemic symbols. Results of the application of the label alignment procedure to EUROMO Italian continuous speech material are presented.

Publication type: 
Contributo in atti di convegno
Author or Creator: 
O. Andersen
Cosi P.
Dalsgaard P.
Source: 
Proceedings Primo Workshop Italiano su "Le reti neuroniche per il trattamento del parlato", pp. 18–29, Roma, Italia, 8-9 November,1990
Date: 
1990
Resource Identifier: 
http://www.cnr.it/prodotto/i/241871
Language: 
Eng
ISTC Author: 
Piero Cosi's picture
Real name: