Temporal sequence classification by memory neuron networks

Author

Poddar, Pinaki ; Rao, P.V.S.

Author_Institution

Comput. Syst. & Commun. Group, Tata Inst. of Fundamental Res., Bombay, India

fYear

1993

fDate

6-9 Sep 1993

Firstpage

181

Lastpage

189

Abstract

A recurrent connectionist architecture, called memory neuron network (MNN), is applied for classification of temporal sequences. The network architecture allows a learnable parametric representation of the activation history of the units. It has been shown that the network is generalized version of network with time-delays. The learning protocol has been developed to train a collection of such networks as discriminant models for classes of temoral sequences. The design is tested in classification of voiced plosives /B/,/D/,/G/. Due to continuous movement of the articulators, the spectral characteristics of the speech signal change during transitions from one phoneme to the other. MNN has been used to model this dynamic behavior during the transitions from plosive sounds to vowels

Keywords

pattern classification; recurrent neural nets; spectral analysis; speech recognition; activation history; continuous articulator movement; discriminant models; learnable parametric representation; learning protocol; memory neuron networks; phoneme transitions; recurrent connectionist architecture; spectral characteristics; temporal sequence classification; voiced plosives; vowels; Computer architecture; Computer networks; Delay; History; Kernel; Multi-layer neural network; Neurons; Pattern classification; Speech; Stochastic processes;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks for Processing [1993] III. Proceedings of the 1993 IEEE-SP Workshop

Conference_Location

Linthicum Heights, MD

Print_ISBN

0-7803-0928-6

Type

conf

DOI

10.1109/NNSP.1993.471871

Filename

471871