Adaptive Training for Voice Conversion Based on Eigenvoices

In this paper, we describe a novel model training method for one-to-many eigenvoice conversion (EVC). One-to-many EVC is a technique for converting a specific source speaker's voice into an arbitrary target speaker's voice. An eigenvoice Gaussian mixture model (EV-GMM) is trained in advanc...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEICE Transactions on Information and Systems 2010/06/01, Vol.E93.D(6), pp.1589-1598
Hauptverfasser:	OHTANI, Yamato, TODA, Tomoki, SARUWATARI, Hiroshi, SHIKANO, Kiyohiro
Format:	Artikel
Sprache:	eng
Schlagworte:	adaptive training Applied sciences Artificial intelligence Computer science control theory systems Conversion Converting eigenvoice Exact sciences and technology Gaussian Gaussian mixture model Information, signal and communications theory Mathematical models Signal processing Speech Speech and sound recognition and synthesis. Linguistics Speech processing speech synthesis Telecommunications and information theory Training Voice voice conversion
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!