Modular connectionist structure for 100-word recognition

Author

Hackbarth, Heidi ; Mantel, Jochen

Author_Institution

SEL Alcatel, Stuttgart, Germany

fYear

1991

fDate

8-14 Jul 1991

Firstpage

845

Abstract

A modular neural structure is presented which is dedicated to the recognition of larger vocabularies. It contains several so-called scaly subnets, assembled into a compound network by neural glue elements. This architecture and the corresponding training scheme have been investigated for various network parameters during speaker-dependent 100-word recognition. Important simulation results were compared with a multilayer perceptron showing scaly input-to-hidden connections and with standard dynamic time warping. Under the criterion of high recognition rates along with very short reaction time, modular subnet assemblies provide for successful recognition of 100 words. They are also recommended for speaker-independent classification

Keywords

neural nets; speech recognition; 100-word recognition; dynamic time warping; modular neural structure; modular subnet assemblies; multilayer perceptron; network parameters; neural glue elements; simulation results; speaker-independent classification; Assembly; Cepstrum; Humans; Multilayer perceptrons; Neural networks; Robustness; Speech; Telephony; Time warp simulation; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1991., IJCNN-91-Seattle International Joint Conference on

Conference_Location

Seattle, WA

Print_ISBN

0-7803-0164-1

Type

conf

DOI

10.1109/IJCNN.1991.155444

Filename

155444