Dirichlet Mixture Models of neural net posteriors for HMM-based speech recognition

In this paper, we present a novel technique for modeling the posterior probability estimates obtained from a neural net work directly in the HMM framework using the Dirichlet Mixture Models (DMMs). Since posterior probability vectors lie on a probability simplex their distribution can be modeled usi...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Balakrishnan, V., Sivaram, G. S. V. S., Khudanpur, Sanjeev
Format:	Tagungsbericht
Sprache:	eng
Schlagworte:	Computational modeling Data models Dirichlet distribution Feature extraction Hidden Markov models HMMs neural network posteriors Probability Speech Training
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!