A new neuron model for an Alphanet-semicontinuous HMM

Author

Diaz-Verdejo, J.E. ; Segura-Luna, J.C. ; Rubio-Ayuso, A.J. ; Peinado-Herreros, A.M. ; Pérez-Córdoba, J.L.

Author_Institution

Dpto. de Electronica y Tecnologia de Computadores, Granada Univ., Spain

Volume

1

fYear

1993

fDate

27-30 April 1993

Firstpage

529

Abstract

The main goal is automatic speech recognition by using artificial neural networks. The authors define a generalized type of neuron that, grouped in a recurrent neural network (an Alphanet), implements a semicontinuous hidden Markov model (SCHMM). The neurons are grouped in a single layer that generates the Alphanet in such a way that some of its inputs come from the outputs. The network allows an interpretation according to SCHMM models, evaluating symbol sequences that constitute the second type of inputs. The network is trained using the backpropagation algorithm and has been applied to an isolated word recognition task. The experimental results show recognition rates reaching multi-speaker recognition rates of 97.81%.<>

Keywords

backpropagation; hidden Markov models; recurrent neural nets; speech recognition; Alphanet; automatic speech recognition; backpropagation algorithm; isolated word recognition; neuron model; recurrent neural network; semicontinuous hidden Markov model; symbol sequences;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1993. ICASSP-93., 1993 IEEE International Conference on

Conference_Location

Minneapolis, MN, USA

ISSN

1520-6149

Print_ISBN

0-7803-7402-9

Type

conf

DOI

10.1109/ICASSP.1993.319172

Filename

319172