发帖
雷达卡
UniSpeech: Unified Speech Representation Learning
with Labeled and Unlabeled Data
Chengyi Wang * 1 Yu Wu 2 Yao Qian 2 Kenichi Kumatani 2 Shujie Liu 2 Furu Wei 2 Michael Zeng 2
Xuedong Huang 2
Abstract majority of the nearly 7000 languages spoken worldwide
In this paper, we propose a unified pre-training (Katzner & Miller, 2002). This poses a real challenge for
approach called UniSpeech to learn speech repre- buildi ...
京公网安备 11010802022788号
