Scaly artificial neural networks for speaker-independent recognition of isolated words

Author

Krause, Andreas ; Hackbarth, Heidi

Author_Institution

Stand. Elektrik Lorenz AG, Stuttgart, West Germany

fYear

1989

fDate

23-26 May 1989

Firstpage

21

Abstract

Artificial neural networks were investigated as an approach to speaker-independent recognition of isolated words from a variable-size vocabulary. A scaly pattern of connecting links between the input and hidden layer was established within a strict feed-forward wiring structure. The amount of training material and vocabulary size as well as the choice of network dimensions, such as the number of layers and input and hidden units, are discussed. Experimental results are reported and compared to the recognition performance obtained with a fully connected layered network. Error rates lower than 5% for vocabularies with up to 20 words suggest that appropriately designed artificial neural networks are well suited for a speaker-independent recognition task

Keywords

neural nets; speech recognition; artificial neural networks; feed-forward wiring structure; isolated word recognition; network dimensions; scaly pattern; speaker-independent recognition; speech recognition; training material; variable-size vocabulary; Artificial neural networks; Error analysis; Feedforward systems; Hidden Markov models; Joining processes; Neural networks; Speech; Testing; Vocabulary; Wiring;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1989. ICASSP-89., 1989 International Conference on

Conference_Location

Glasgow

ISSN

1520-6149

Type

conf

DOI

10.1109/ICASSP.1989.266353

Filename

266353