SLP-L14.6
DYNAMIC-SUPERB: TOWARDS A DYNAMIC, COLLABORATIVE, AND COMPREHENSIVE INSTRUCTION-TUNING BENCHMARK FOR SPEECH
Chien-yu Huang, Ke-Han Lu, Shih-Heng Wang, Chun-Yi Kuan, Chi-Yuan Hsiao, Haibin Wu, National Taiwan University, Taiwan; Siddhant Arora, Carnegie Mellon University, United States of America; Kai-Wei Chang, National Taiwan University, Taiwan; Jiatong Shi, Yifan Peng, Roshan Sharma, Shinji Watanabe, Bhiksha Ramakrishnan, Carnegie Mellon University, United States of America; Shady Shehata, Mohamed bin Zayed University of Artificial Intelligence, United Arab Emirates; Hung-yi Lee, National Taiwan University, Taiwan
Session:
SLP-L14: Self-supervised learning for speech processing I Lecture
Track:
Speech and Language Processing
Location:
Room 205A
Presentation Time:
Wed, 17 Apr, 14:50 - 15:10 (UTC +9)
Session Co-Chairs:
Wei-Ning Hsu, Meta and Suwon Shon, ASAPP
Session SLP-L14
SLP-L14.1: ARE SOFT PROMPTS GOOD ZERO-SHOT LEARNERS FOR SPEECH RECOGNITION?
Dianwen Ng, Alibaba Group; Nanyang Technological University, Singapore; Chong Zhang, Alibaba Group, Singapore; Ruixi Zhang, NA, Singapore; Yukun Ma, Alibaba Group, Singapore; Fabian Ritter-Gutierrez, Nanyang Technological University; A-Star, Singapore; Trung Hieu Nguyen, Chongjia Ni, Shengkui Zhao, Alibaba Group, Singapore; Eng Siong Chng, Nanyang Technological University, Singapore; Bin Ma, Alibaba Group, Singapore
SLP-L14.2: TOWARDS UNIVERSAL SPEECH DISCRETE TOKENS: A CASE STUDY FOR ASR AND TTS
Yifan Yang, Feiyu Shen, Chenpeng Du, Ziyang Ma, Kai Yu, MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, China; Daniel Povey, Xiaomi Corporation, China; Xie Chen, MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, China
SLP-L14.3: UNSUPERVISED SPEECH RECOGNITION WITH N-SKIPGRAM AND POSITIONAL UNIGRAM MATCHING
Liming Wang, Mark Hasegawa-Johnson, University of Illinois Urbana-Champaign, United States of America; Chang Yoo, KAIST, Korea, Republic of
SLP-L14.4: BRAVEN: IMPROVING SELF-SUPERVISED PRE-TRAINING FOR VISUAL AND AUDITORY SPEECH RECOGNITION
Alexandros Haliassos, Andreas Zinonos, Rodrigo Mira, Imperial College London, United Kingdom of Great Britain and Northern Ireland; Stavros Petridis, Maja Pantic, Meta, United Kingdom of Great Britain and Northern Ireland
SLP-L14.5: REVISITING SELF-SUPERVISED LEARNING OF SPEECH REPRESENTATION FROM A MUTUAL INFORMATION PERSPECTIVE
Alexander Liu, MIT, United States of America; Sung-Lin Yeh, University of Edinburgh, United Kingdom of Great Britain and Northern Ireland; James Glass, MIT, United States of America
SLP-L14.6: DYNAMIC-SUPERB: TOWARDS A DYNAMIC, COLLABORATIVE, AND COMPREHENSIVE INSTRUCTION-TUNING BENCHMARK FOR SPEECH
Chien-yu Huang, Ke-Han Lu, Shih-Heng Wang, Chun-Yi Kuan, Chi-Yuan Hsiao, Haibin Wu, National Taiwan University, Taiwan; Siddhant Arora, Carnegie Mellon University, United States of America; Kai-Wei Chang, National Taiwan University, Taiwan; Jiatong Shi, Yifan Peng, Roshan Sharma, Shinji Watanabe, Bhiksha Ramakrishnan, Carnegie Mellon University, United States of America; Shady Shehata, Mohamed bin Zayed University of Artificial Intelligence, United Arab Emirates; Hung-yi Lee, National Taiwan University, Taiwan
Contacts