SLP-L24: Resource Constrained Acoustic and Langugage Modeling
Thu, 18 Apr, 16:30 - 18:30 (UTC +9)
Location: Room E3
Session Type: Lecture
Session Co-Chairs: Xiaodong Cui, IBM Research and Zhijian Ou, Tsinghua University
Track: Speech and Language Processing
Click the to view the manuscript on IEEE Xplore Open Preview
Thu, 18 Apr, 16:30 - 16:50 (UTC +9)
 

SLP-L24.1: TOWARDS AUTOMATIC DATA AUGMENTATION FOR DISORDERED SPEECH RECOGNITION
Zengrui Jin, The Chinese University of Hong Kong, Hong Kong; Xurong Xie, Chinese Academy of Sciences, China; Tianzi Wang, Mengzhe Geng, Jiajun Deng, Guinan Li, Shujie Hu, Xunying Liu, The Chinese University of Hong Kong, Hong Kong
Thu, 18 Apr, 16:50 - 17:10 (UTC +9)
 

SLP-L24.2: SOFT ALIGNMENT OF MODALITY SPACE FOR END-TO-END SPEECH TRANSLATION
Yuhao Zhang, Kaiqi Kou, Bei Li, Northeastern University, China; Chen Xu, Harbin Engineering University, China; Chunliang Zhang, Tong Xiao, Jingbo Zhu, Northeastern University, China
Thu, 18 Apr, 17:10 - 17:30 (UTC +9)
 

SLP-L24.3: GENERATIVE CONTEXT-AWARE FINE-TUNING OF SELF-SUPERVISED SPEECH MODELS
Suwon Shon, Kwangyoun Kim, Prashant Sridhar, Yi-Te Hsu, ASAPP, United States of America; Shinji Watanabe, Carnegie Mellon University, United States of America; Karen Livescu, Toyota Technological Institute at Chicago, United States of America
Thu, 18 Apr, 17:30 - 17:50 (UTC +9)
 

SLP-L24.4: EXTENDING LARGE LANGUAGE MODELS FOR SPEECH AND AUDIO CAPTIONING
Changli Tang, Wenyi Yu, Guangzhi Sun, Tsinghua University, China; Xianzhao Chen, Tian Tan, Wei Li, Lu Lu, Zejun Ma, ByteDance, China; Chao Zhang, Tsinghua University, China
Thu, 18 Apr, 17:50 - 18:10 (UTC +9)
 

SLP-L24.5: HYSTOC: OBTAINING WORD CONFIDENCES FOR FUSION OF END-TO-END ASR SYSTEMS
Karel Beneš, Martin Kocour, Lukáš Burget, Brno University of Technology, Czechia
Thu, 18 Apr, 18:10 - 18:30 (UTC +9)
 

SLP-L24.6: EFFECTIVE INTERNAL LANGUAGE MODEL TRAINING AND FUSION FOR FACTORIZED TRANSDUCER MODEL
Jinxi Guo, Niko Moritz, YIngyi Ma, Frank Seide, Chunyang Wu, Jay Mahadeokar, Ozlem Kalinli, Christian Fuegen, Mike Seltzer, Meta, United States of America