We introduce a language modeling approach for text to speech synthesis (...
The massive growth of self-supervised learning (SSL) has been witnessed ...
Self-supervised speech pre-training empowers the model with the contextu...
There is a surge in interest in self-supervised learning approaches for
...
How to boost speech pre-training with textual data is an unsolved proble...
Transformer has been successfully applied to speech separation recently ...
Recently, self-supervised learning (SSL) has demonstrated strong perform...
Recently, pioneer work finds that speech pre-trained models can solve
fu...
Self-supervised learning (SSL) achieves great success in speech recognit...
The speech representations learned from large-scale unlabeled data have ...
Self-supervised learning (SSL) is a long-standing goal for speech proces...
Speech separation has been successfully applied as a frontend processing...
Slot filling, a fundamental module of spoken language understanding, oft...
With its strong modeling capacity that comes from a multi-head and
multi...
This paper describes the Microsoft speaker diarization system for monaur...
Continuous speech separation plays a vital role in complicated speech re...
Deep pretrained language models have achieved great success in the way o...