Audio-Language Models

Follow this topic Ask about this topic

Momentum

36 papers in the last four weeks, up 414% on the four weeks before. 0.4% of all new papers.

Jul 13Week of Sep 28

Latest papers 184

All topics

Aligning Audio Captions with Human Preferences
Sep 18, 2025Kartik Hegde, Rehana Mahfuz, Yinyi Guo +1Reward Modeling Audio-Language Models
Qualcomm Technologies, Inc., India · Qualcomm Technologies, Inc., USA
The NTNU System at the S&I Challenge 2025 SLA Open Track
Jun 5, 2025Hong-Yun Lin, Tien-Hong Lo, Yu-Hsuan Fang +4Audio-Language Models Automated Evaluation
Department of Computer Science and Information Engineering, National Taiwan Normal University, Taiwan · Institute of AI Interdisciplinary Applied Technology, National Taiwan Normal University, Taiwan
Audio-Language Models for Audio-Centric Tasks: A Systematic Survey
Jan 25, 2025Yi Su, Jisheng Bai, Qisheng Xu +2Audio Representation Learning Audio Understanding
College of Computer Science and Technology, National University of Defense Technology, Changsha, China · School of Communications and Information Engineering, Xi’an University of Posts and Telecommunications, Xi’an, China
Aslema at NADI 2026: Data Augmentation for Intent Recognition and Slot Filling
Date pendingTajwaar Shafiq, Hunzalah Hassan Bhatti, Firoj Alam +1Spoken Language Understanding Synthetic Data Augmentation
Qatar Computing Research Institute, HBKU, Qatar

Sep 18, 2025, eess.ASJ/K move · Enter open · S save

Aligning Audio Captions with Human Preferences

Kartik Hegde, Rehana Mahfuz, Yinyi Guo, Erik Visser

Qualcomm Technologies, Inc., India · Qualcomm Technologies, Inc., USA

Reward Modeling Audio-Language Models Audio Captioning Preference Alignment RL from Human Feedback

Open paper AskPDF arXiv

Current audio captioning relies on supervised learning with paired audio-caption data, which is costly to curate and may not reflect human preferences in real-world scenarios. To address this, we propose a preference-aligned audio captioning framework based on Reinforcement Learning from Human Feedback (RLHF). To capture nuanced preferences, we train a Contrastive Language-Audio Pretraining (CLAP) based reward model using human-labeled pairwise preference data. This reward model is integrated into an RL framework to fine-tune any baseline captioning system without ground-truth annotations. Extensive human evaluations across multiple datasets show that our method produces captions preferred over baseline models, particularly when baselines fail to provide correct and natural captions. Furthermore, our framework achieves performance comparable to supervised approaches with ground-truth data, demonstrating effective alignment with human preferences and scalability in real-world use.

Momentum

Related topics

Latest papers 184

Aligning Audio Captions with Human Preferences

The NTNU System at the S&I Challenge 2025 SLA Open Track

Audio-Language Models for Audio-Centric Tasks: A Systematic Survey

Aslema at NADI 2026: Data Augmentation for Intent Recognition and Slot Filling