216 citations · 540 across the 33 of their papers we have counts for
Showing 2023Show all
3 papers · 1 filter
cs.SD2023
Text-Only Domain Adaptation for End-to-End Speech Recognition through Down-Sampling Acoustic Representation
Jiaxu Zhu, Weinan Tong, Yaoxun Xu +6
Mapping two modalities, speech and text, into a shared representation space, is a research topic of using text-only data to improve end-to-end automatic speech recognition (ASR) pe…
cs.LG2023
Model Debiasing via Gradient-based Explanation on Representation
Jindi Zhang, Luning Wang, Dan Su +3
Machine learning systems produce biased results towards certain demographic groups, known as the fairness problem. Recent approaches to tackle this problem learn a latent code (i.e…
eess.AS2023
TriNet: stabilizing self-supervised learning from complete or slow collapse on ASR
Lixin Cao, Jun Wang, Ben Yang +2
Self-supervised learning (SSL) models confront challenges of abrupt informational collapse or slow dimensional collapse. We propose TriNet, which introduces a novel triple-branch a…