Segregation of Speakers for Speaker Adaptation in TV News Audio

Speaker adaptation is commonly used to compensate speaker variation in large vocabulary continuous speech recognition. In a multi-speaker environment where speakers change frequently speaker segregation is needed to divide the input audio stream to speaker turns. Speaker turns define the current spe...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Remes, U., Pylkkonen, J., Kurimo, M.
Format:	Tagungsbericht
Sprache:	eng
Schlagworte:	Covariance matrix Informatics Maximum likelihood decoding Maximum likelihood linear regression Shape measurement speaker recognition Speech recognition Streaming media Testing Vocabulary
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!