Streaming End-to-End Multilingual Speech Recognition with Joint Language Identification

Language identification is critical for many downstream tasks in automatic speech recognition (ASR), and is beneficial to integrate into multilingual end-to-end ASR as an additional task. In this paper, we propose to modify the structure of the cascaded-encoder-based recurrent neural network transdu...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2022-09
Hauptverfasser:	Zhang, Chao, Li, Bo, Sainath, Tara, Strohman, Trevor, Mavandadi, Sepand, Chang, Shuo-yiin, Haghani, Parisa
Format:	Artikel
Sprache:	eng
Schlagworte:	Automatic speech recognition Coders Context Recurrent neural networks
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!