Multilingual acoustic modeling for speech recognition based on subspace Gaussian Mixture Models

Although research has previously been done on multilingual speech recognition, it has been found to be very difficult to improve over separately trained systems. The usual approach has been to use some kind of "universal phone set" that covers multiple languages. We report experiments on a...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Burget, L, Schwarz, P, Agarwal, M, Akyazi, P, Kai Feng, Ghoshal, A, Glembek, O, Goel, N, Karafiát, M, Povey, D, Rastrow, A, Rose, R C, Thomas, S
Format:	Tagungsbericht
Sprache:	eng
Schlagworte:	Automatic speech recognition Availability Hidden Markov models Humans Large vocabulary speech recognition Multilingual acoustic modeling Natural languages Robustness Space technology Speech recognition Subspace constraints Subspace Gaussian mixture model Training data
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!