Multiple sequence alignment based bootstrapping for improved incremental word learning

We investigate incremental word learning with few training examples in a Hidden Markov Model (HMM) framework suitable for an interactive learning scenario with little prior knowledge. When using only a few training examples the initialization of the models is a crucial step. In the bootstrapping app...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Clemente, I A, Heckmann, M, Sagerer, G, Joublin, F
Format:	Tagungsbericht
Sprache:	eng
Schlagworte:	Automatic speech recognition Cognition Cognitive robotics Decoding Hidden Markov models Maximum likelihood estimation sequence estimation Speech recognition training Training data Viterbi algorithm
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!