A novel approach for classifying continuous speech into visible mouth-shape related classes

Author

Luo, S.-H. ; King, R.W.

Author_Institution

Dept. of Electr. Eng., Sydney Univ., NSW, Australia

fYear

1994

fDate

19-22 Apr 1994

Abstract

The paper describes a novel approach for classifying continuous speech into visible mouth-shape related classes (called visemes). The selection and comparison of various acoustic speech features and the use of context information in the classification are addressed. Continuous speech is classified into 9 visible mouth-shape related classes on an acoustic frame basis. Some mouth-shape related acoustic speech signal features are selected as the input to a classifier constructed with recurrent neural network (RNN). 304 training sentences and 88 testing sentences are chosen from DARPA TIMIT continuous speech database. The average viseme recognition rate for the test set reaches 84.7% on frame level, which is a quite promising result considering that the test is applied on continuous multi-speakers and large vocabulary speech

Keywords

learning (artificial intelligence); recurrent neural nets; speech processing; speech recognition; DARPA TIMIT continuous speech databas; acoustic frame basis; acoustic speech features; acoustic speech signal feature; classification; context information; continuous speech; large vocabulary speech; multi-speakers; recurrent neural network; testing sentences; training sentences; viseme recognition rate; visemes; visible mouth-shape related classes; Acoustic testing; Image coding; Layout; Mouth; Mutual information; Recurrent neural networks; Signal analysis; Speech analysis; Speech coding; Speech enhancement;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1994. ICASSP-94., 1994 IEEE International Conference on

Conference_Location

Adelaide, SA

ISSN

1520-6149

Print_ISBN

0-7803-1775-0

Type

conf

DOI

10.1109/ICASSP.1994.389255

Filename

389255