An acoustic segment model approach to incorporating temporal information into speaker modeling for text-independent speaker recognition

We propose an acoustic segment model (ASM) approach to incorporating temporal information into speaker modeling in text-independent speaker recognition. In training, the proposed framework first estimates a collection of ASM-based universal background models (UBMs). Multiple sets of speaker-specific...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Yu Tsao, Hanwu Sun, Haizhou Li, Chin-Hui Lee
Format:	Tagungsbericht
Sprache:	eng
Schlagworte:	acoustic segment model Clustering algorithms Hidden Markov models Iterative algorithms Loudspeakers Natural languages Partitioning algorithms Pattern classification Quantization Speaker recognition Testing
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!