SLP-P31.8
WINDOWED SUMMARYMIXING: AN EFFICIENT FINE-TUNING OF SELF-SUPERVISED LEARNING MODELS FOR LOW-RESOURCE SPEECH RECOGNITION
Aditya Srinivas Menon, Kumud Tripathi, Raj Gohil, Pankaj Wasnik, SRI, India
Session:
SLP-P31: Self-supervised and Unsupervised Domain Adaptation for ASR Poster
Track:
Speech and Language Processing [SL]
Location:
Poster Area 27
Presentation Time:
Thu, 7 May, 09:00 - 11:00
Presentation
Discussion
Resources
No resources available.
Session SLP-P31
SLP-P31.1: Synthesized Data Selection via Score Distribution Matching for Te Reo Māori Automatic Speech Recognition
Zhihan Wang, Feng Hou, Ruili Wang, Massey University, New Zealand
SLP-P31.2: POSITION-INVARIANT FINE-TUNING OF SPEECH ENHANCEMENT MODELS WITH SELF-SUPERVISED SPEECH REPRESENTATIONS
Amit Meghanani, Thomas Hain, The University of Sheffield, United Kingdom of Great Britain and Northern Ireland
SLP-P31.3: IMPROVING AUTOMATIC SPEECH RECOGNITION BY MITIGATING DISTORTIONS INTRODUCED BY SPEECH ENHANCEMENT UNDER DRONE NOISE
Ryusei Miura, Takahiro Osaki, Benjamin Yen, Takeshi Ashizawa, Kazuhiro Nakadai, Institute of Science Tokyo, Japan
SLP-P31.4: TEACHING THE TEACHERS: BOOSTING UNSUPERVISED DOMAIN ADAPTATION IN SPEECH RECOGNITION BY ENSEMBLE UPDATE
Rehan Ahmad, University of Sheffield, United Kingdom of Great Britain and Northern Ireland; Muhammad Umar Farooq, Emotech, United Kingdom of Great Britain and Northern Ireland; Qihang Feng, Thomas Hain, University of Sheffield, United Kingdom of Great Britain and Northern Ireland
SLP-P31.5: INVERSE-HESSIAN REGULARIZATION FOR CONTINUAL LEARNING IN ASR
Steven Vander Eeckt, Hugo Van hamme, KU Leuven, Belgium
SLP-P31.6: BEST-RQ-BASED SELF-SUPERVISED LEARNING FOR WHISPER DOMAIN ADAPTATION
Raphaël Bagat, CNRS, France; Irina Illina, Université de Lorraine, France; Emmanuel Vincent, Inria, France
SLP-P31.7: CCST: Cross-Modal and Consistency-Aware Self-Training for Source-Free Unsupervised Domain Adaptation in Speech Recognition
Yuan Li, Yonghe Wang, ZhenJie Gao, Feilong Bao, Inner Mongolia University, China
SLP-P31.8: WINDOWED SUMMARYMIXING: AN EFFICIENT FINE-TUNING OF SELF-SUPERVISED LEARNING MODELS FOR LOW-RESOURCE SPEECH RECOGNITION
Aditya Srinivas Menon, Kumud Tripathi, Raj Gohil, Pankaj Wasnik, SRI, India
SLP-P31.9: PROFICIENCY-AWARE ADAPTATION AND DATA AUGMENTATION FOR ROBUST L2 ASR
Ling Sun, Charlotte Zhu, Shuju Shi, Indiana University Bloomington, United States of America
SLP-P31.10: DOMAIN-AWARE SCHEDULING FOR ASR FINE-TUNING
Nikolaos Lagos, Ioan Calapodescu, Naver Labs Europe, France
Contacts