Adaptive transition bias for robust low complexity speech recognition

The basis for all methods described in this paper is the application of an adaptive transition bias to the sequences of phoneme models that represent spoken utterances. This offers significantly improved accuracy in phoneme based speaker independent recognition, while adding very little overhead to...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Koumpis, K., Riis, S.K.
Format:	Tagungsbericht
Sprache:	eng
Schlagworte:	Error analysis Hidden Markov models Maximum likelihood linear regression Mobile handsets Multi-layer neural network Neural networks Noise robustness Signal to noise ratio Speech recognition Testing
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!