2 papers
eess.AS2022
Progressive Multi-Scale Self-Supervised Learning for Speech Recognition
Genshun Wan, Tan Liu, Hang Chen +3
Self-supervised learning (SSL) models have achieved considerable improvements in automatic speech recognition (ASR). In addition, ASR performance could be further improved if the m…
cs.CL2021
Topic Classification on Spoken Documents Using Deep Acoustic and Linguistic Features
Tan Liu, Wu Guo, Bin Gu
Topic classification systems on spoken documents usually consist of two modules: an automatic speech recognition (ASR) module to convert speech into text and a text topic classific…