A time-delay neural network architecture for isolated word recognition

A translation-invariant back-propagation network is described that performs better than a sophisticated continuous acoustic parameter hidden Markov model on a noisy, 100-speaker confusable vocabulary isolated word recognition task. The network's replicated architecture permits it to extract pre...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Neural networks 1990, Vol.3 (1), p.23-43
Hauptverfasser:	Lang, Kevin J., Waibel, Alex H., Hinton, Geoffrey E.
Format:	Artikel
Sprache:	eng
Schlagworte:	Applied sciences Constrained links Exact sciences and technology Information, signal and communications theory Isolated word recognition Multiresolution learning Multispeaker speech recognition Network architecture Neural networks Signal processing Speech processing Telecommunications and information theory Time delays
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	A translation-invariant back-propagation network is described that performs better than a sophisticated continuous acoustic parameter hidden Markov model on a noisy, 100-speaker confusable vocabulary isolated word recognition task. The network's replicated architecture permits it to extract precise information from unaligned training patterns selected by a naive segmentation rule.
ISSN:	0893-6080 1879-2782
DOI:	10.1016/0893-6080(90)90044-L