SLP-P36.1
WHISPER-MLA: REDUCING GPU MEMORY CONSUMPTION OF ASR MODELS BASED ON MHA2MLA CONVERSION
Sen Zhang, Jianguo Wei, Wenhuan Lu, Xianghu Yue, College of Intelligence and Computing, Tianjin University, China; Wei Li, Qiang Li, Pengcheng Zhao, Ming Cai, Luo Si, Banma Network Technology Co., Ltd., China
Session:
SLP-P36: Personalized Speech Recognition Poster
Track:
Speech and Language Processing [SL]
Location:
Poster Area 32
Presentation Time:
Thu, 7 May, 09:00 - 11:00
Presentation
Discussion
Resources
No resources available.
Session SLP-P36
SLP-P36.1: WHISPER-MLA: REDUCING GPU MEMORY CONSUMPTION OF ASR MODELS BASED ON MHA2MLA CONVERSION
Sen Zhang, Jianguo Wei, Wenhuan Lu, Xianghu Yue, College of Intelligence and Computing, Tianjin University, China; Wei Li, Qiang Li, Pengcheng Zhao, Ming Cai, Luo Si, Banma Network Technology Co., Ltd., China
SLP-P36.2: MIND THE SHIFT: USING DELTA SSL EMBEDDINGS TO ENHANCE CHILD ASR
Zilai Wang, Univerisity of California, Los Angeles, United States of America; Natarajan Balaji Shankar, University of California, Los Angeles, United States of America; Kaiyuan Zhang, Zihan Wang, Abeer Alwan, Univerisity of California, Los Angeles, United States of America
SLP-P36.3: PROBING WHISPER FOR DYSARTHRIC SPEECH IN DETECTION AND ASSESSMENT
Zhengjun Yue, Devendra Kayande, TU Delft, Netherlands; Zoran Cvetkovic, King's College London, United Kingdom of Great Britain and Northern Ireland; Erfan Loweimi, Cisco, United Kingdom of Great Britain and Northern Ireland
SLP-P36.4: LISTEN, BUT DON'T LEAK: SENSITIVE DATA PROTECTION FOR PRIVACY AWARE AUTOMATIC SPEECH RECOGNITION WITH ACOUSTIC TRIGGERS
Trinita Roy, Ngoc Thang Vu, University of Stuttgart, Germany
SLP-P36.5: BAYESIAN LOW-RANK FACTORIZATION FOR ROBUST MODEL ADAPTATION
Enes Yavuz Ugan, Karlsruhe Institute of Technology, Germany; Ngoc-Quan Pham, Carnegie Mellon University, United States of America; Alexander Waibel, Karlsruhe Institute of Technology, Germany
SLP-P36.6: EDGESPOT: EFFICIENT AND HIGH-PERFORMANCE FEW-SHOT MODEL FOR KEYWORD SPOTTING
Oguzhan Buyuksolak, Alican Gok, Osman Erman Okman, Analog Devices, Türkiye
SLP-P36.7: PHOENIXDSR: PHONEME-GUIDED AND LLM-ENHANCED DYSARTHRIC SPEECH RECOGNITION
Yuxuan Wu, Yifan Xu, Junkun Wang, Xin Zhao, Jiayong Jiang, Zhaojie Luo, Southeast University, China
SLP-P36.8: Confidence-Guided Error Correction for Disordered Speech Recognition
Abner Hernandez, Tomás Arias Vergara, Andreas Maier, Paula Andrea Pérez-Toro, Friedrich Alexander University Erlangen Nürnberg, Germany
SLP-P36.9: Advancing Semi-Supervised Child Speech Recognition with Omni-Temporal Classification under Label Noise
Jiamin Xie, John Hansen, University of Texas at Dallas, United States of America
SLP-P36.10: Variational Low-Rank Adaptation for Personalized Impaired Speech Recognition
Niclas Pokel, Technical University of Munich, Germany; Pehuen Moure, Roman Boehringer, Shih-Chii Liu, University of Zurich and ETH Zurich, Switzerland; Yingqian Gao, University of Zurich, Switzerland
Contacts