Scaling Up Online Speech Recognition Using ConvNets

We design an online end-to-end speech recognition system based on Time-Depth Separable (TDS) convolutions and Connectionist Temporal Classification (CTC). We improve the core TDS architecture in order to limit the future context and hence reduce latency while maintaining accuracy. The system has alm...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Pratap, Vineel, Xu, Qiantong, Kahn, Jacob, Avidov, Gilad, Likhomanenko, Tatiana, Hannun, Awni, Liptchinsky, Vitaliy, Synnaeve, Gabriel, Collobert, Ronan
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!