Efficient CTC Regularization via Coarse Labels for End-to-End Speech Translation

For end-to-end speech translation, regularizing the encoder with the Connectionist Temporal Classification (CTC) objective using the source transcript or target translation as labels can greatly improve quality metrics. However, CTC demands an extra prediction layer over the vocabulary space, bringi...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Zhang, Biao, Haddow, Barry, Sennrich, Rico
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Computation and Language Computer Science - Sound
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!