Wise teachers train better DNN acoustic models

Automatic speech recognition is becoming more ubiquitous as recognition performance improves, capable devices increase in number, and areas of new application open up. Neural network acoustic models that can utilize speaker-adaptive features, have deep and wide layers, or more computationally expens...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	EURASIP journal on audio, speech, and music processing speech, and music processing, 2016-04, Vol.2016 (1), p.1, Article 10
Hauptverfasser:	Price, Ryan, Iso, Ken-ichi, Shinoda, Koichi
Format:	Artikel
Sprache:	eng
Schlagworte:	Acoustics Deep Learning for Speech and Language Processing Applications Engineering Engineering Acoustics Mathematics in Music Signal,Image and Speech Processing
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!