Pretraining Enhanced RNN Transducer

Recurrent neural network transducer (RNN-T) is an important branch of current end-to-end automatic speech recognition (ASR). Various promising approaches have been designed for boosting RNN-T architecture; however, few studies exploit the effectiveness of pretrained methods in this framework. In thi...

Πλήρης περιγραφή

Λεπτομέρειες βιβλιογραφικής εγγραφής

Κύριοι συγγραφείς:	Junyu Lu, Rongzhong Lian, Di Jiang, Yuanfeng Song, Zhiyang Su, Victor Junqiu Wei, Lin Yang
Μορφή:	Artigo
Γλώσσα:	Inglês
Έκδοση:	Tsinghua University Press 2024-12-01
Σειρά:	CAAI Artificial Intelligence Research
Θέματα:	pretraining automatic speech recognition self-supervised learning
Διαθέσιμο Online:	https://www.sciopen.com/article/10.26599/AIR.2024.9150039
Ετικέτες:	Προσθήκη ετικέτας Δεν υπάρχουν, Καταχωρήστε ετικέτα πρώτοι!