Deep Belief Neural Networks and Bidirectional Long-Short Term Memory Hybrid for Speech Recognition

This paper describes a Deep Belief Neural Network (DBNN) and Bidirectional Long-Short Term Memory (LSTM) hybrid used as an acoustic model for Speech Recognition. It was demonstrated by many independent researchers that DBNNs exhibit superior performance to other known machine learning frameworks in...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Archives of acoustics 2015-06, Vol.40 (2), p.191-195
Hauptverfasser:	Brocki, Łukasz, Marasek, Krzysztof
Format:	Artikel
Sprache:	eng
Schlagworte:	bidirectional recurrent neural networks deep belief neural networks large vocabulary continuous speech recognition long-short term memory speech recognition
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!