AASP-L9.2
IMPROVING AUDIO CAPTIONING MODELS WITH FINE-GRAINED AUDIO FEATURES, TEXT EMBEDDING SUPERVISION, AND LLM MIX-UP AUGMENTATION
Shih-Lun Wu, Xuankai Chang, Carnegie Mellon University, United States of America; Gordon Wichern, Mitsubishi Electric Research Laboratories, United States of America; Jee-weon Jung, Carnegie Mellon University, United States of America; François Germain, Jonathan Le Roux, Mitsubishi Electric Research Laboratories, United States of America; Shinji Watanabe, Carnegie Mellon University, United States of America
Session:
AASP-L9: Audio-Language Processing and Audio Captioning Lecture
Track:
Audio and Acoustic Signal Processing
Location:
Room E1
Presentation Time:
Thu, 18 Apr, 13:30 - 13:50 (UTC +9)
Session Co-Chairs:
Jonathan Le Roux, Mitsubishi Electric Research Laboratories and Wenwu Wang, University of Surrey
Session AASP-L9
AASP-L9.1: TRAINING AUDIO CAPTIONING MODELS WITHOUT AUDIO
Soham Deshmukh, Benjamin Elizalde, Dimitra Emmanouilidou, Microsoft, United States of America; Bhiksha Raj, Rita Singh, Huaming Wang, Carnegie Mellon University, United States of America
AASP-L9.2: IMPROVING AUDIO CAPTIONING MODELS WITH FINE-GRAINED AUDIO FEATURES, TEXT EMBEDDING SUPERVISION, AND LLM MIX-UP AUGMENTATION
Shih-Lun Wu, Xuankai Chang, Carnegie Mellon University, United States of America; Gordon Wichern, Mitsubishi Electric Research Laboratories, United States of America; Jee-weon Jung, Carnegie Mellon University, United States of America; François Germain, Jonathan Le Roux, Mitsubishi Electric Research Laboratories, United States of America; Shinji Watanabe, Carnegie Mellon University, United States of America
AASP-L9.3: RECAP: RETRIEVAL-AUGMENTED AUDIO CAPTIONING
Sreyan Ghosh, Sonal Kumar, Chandra Kiran Reddy Evuru, Ramani Duraiswami, Dinesh Manocha, University of Maryland, College Park, United States of America
AASP-L9.4: AUDIO DIFFERENCE LEARNING FOR AUDIO CAPTIONING
Tatsuya Komatsu, Yusuke Fujita, LINE, Japan; Kazuya Takeda, Tomoki Toda, Nagoya University, Japan
AASP-L9.5: LEARNING AUDIO CONCEPTS FROM COUNTERFACTUAL NATURAL LANGUAGE
Ali Vosoughi, University of Rochester, United States of America; Luca Bondi, Ho-Hsiang Wu, Bosch Research & Technology Center, United States of America; Chenliang Xu, University of Rochester, United States of America
AASP-L9.6: Transferable Models for Bioacoustics with Human Language Supervision
David Robinson, Independent, Australia; Adelaide Robinson, University of Santa Barbara, United States of America; Lily Akrapongpisak, University of Queensland, Australia
Contacts