activity
20102023
most citedDeep Long Audio Inpainting

23 citations · 235 across the 69 of their papers we have counts for

collaborators

127 papers

cs.CL2023

Revealing the Blind Spot of Sentence Encoder Evaluation by HEROS

Cheng-Han Chiang, Yung-Sung Chuang, James Glass +1

Existing sentence textual similarity benchmark datasets only use a single number to summarize how similar the sentence encoder's decision is to humans'. However, it is unclear what…

cs.CL2022

Introducing Semantics into Speech Encoders

Derek Xu, Shuyan Dong, Changhan Wang +10

Recent studies find existing self-supervised speech encoders contain primarily acoustic rather than semantic information. As a result, pipelined supervised automatic speech recogni…

cs.CL20221 cited

Bridging Speech and Textual Pre-trained Models with Unsupervised ASR

Jiatong Shi, Chan-Jan Hsu, Holam Chung +5

Spoken language understanding (SLU) is a task aiming to extract high-level semantics from spoken utterances. Previous works have investigated the use of speech self-supervised mode…

cs.CL2022

T5lephone: Bridging Speech and Text Self-supervised Models for Spoken Language Understanding via Phoneme level T5

Chan-Jan Hsu, Ho-Lam Chung, Hung-yi Lee +1

In Spoken language understanding (SLU), a natural solution is concatenating pre-trained speech models (e.g. HuBERT) and pretrained language models (PLM, e.g. T5). Most previous wor…

cs.CL2022

SUPERB @ SLT 2022: Challenge on Generalization and Efficiency of Self-Supervised Speech Representation Learning

Tzu-hsun Feng, Annie Dong, Ching-Feng Yeh +11

We present the SUPERB challenge at SLT 2022, which aims at learning self-supervised speech representation for better performance, generalization, and efficiency. The challenge buil…

cs.CL2022

On the Utility of Self-supervised Models for Prosody-related Tasks

Guan-Ting Lin, Chi-Luen Feng, Wei-Ping Huang +5

Self-Supervised Learning (SSL) from speech data has produced models that have achieved remarkable performance in many tasks, and that are known to implicitly represent many aspects…