activity
20132023
most citedWavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing

1.9k citations · 3.5k across the 108 of their papers we have counts for

collaborators
Showing 2023 · cs.SDShow all

1 paper · 2 filters

cs.SD2023

Improving Contextual Spelling Correction by External Acoustics Attention and Semantic Aware Data Augmentation

Xiaoqiang Wang, Yanqing Liu, Jinyu Li +1

We previously proposed contextual spelling correction (CSC) to correct the output of end-to-end (E2E) automatic speech recognition (ASR) models with contextual information such as…