Speaker adaptation by hierarchical EigenVoice

We propose a novel speaker adaptation method, hierarchical EigenVoice (HEV). This method extends the eigenvoice through clustering the Gaussian components of HMMs into a hierarchical tree structure. It enables one to autonomously control a number of adaptation parameters (model complexity) depending...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Onishi, Y., Iso, K.-I.
Format:	Tagungsbericht
Sprache:	eng ; jpn
Schlagworte:	Adaptation model Hidden Markov models Hybrid electric vehicles Laboratories Loudspeakers Maximum likelihood linear regression Principal component analysis Speech recognition Tree data structures
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!