Bayesian Adaptive Inference and Adaptive Training

Large-vocabulary speech recognition systems are often built using found data, such as broadcast news. In contrast to carefully collected data, found data normally contains multiple acoustic conditions, such as speaker or environmental noise. Adaptive training is a powerful approach to build systems...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on audio, speech, and language processing speech, and language processing, 2007-08, Vol.15 (6), p.1932-1943
Hauptverfasser:	Kai Yu, Gales, M.J.F.
Format:	Artikel
Sprache:	eng
Schlagworte:	Acoustic noise Acoustics Adaptive training Applied sciences Bayesian adaptation Bayesian analysis Bayesian inference Bayesian methods Broadcasting Construction Exact sciences and technology incremental Inference Information, signal and communications theory Loudspeakers Mathematical models Maximum likelihood estimation Power system modeling Programmable control Robustness Signal and communications theory Signal processing Signal representation. Spectral analysis Signal, noise Speech processing Speech recognition Studies Telecommunications and information theory Testing Training variational Bayes Working environment noise
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!