5 papers
Masked Diffusion Modeling for Anomaly Detection
Lixing Zhang, Yuchen Liang, Liyan Xie
Anomaly detection aims to identify samples that deviate from the nominal data distribution and is central to many safety-critical applications. However, developing effective anomal…
Audio Jailbreaks in Large Audio-Language Models: Taxonomy, Attack-Defense Analysis, and Cost-Aware Evaluation
Bo-Han Feng, Yu-Hsuan Li Liang, Chien-Feng Liu +2
Large Audio Language Models (LALMs) expand jailbreak risks from token-level prompting to the full speech perception-to-reasoning pipeline, where unsafe behavior can be induced thro…
Pseudo2Real: Task Arithmetic for Pseudo-Label Correction in Automatic Speech Recognition
Yi-Cheng Lin, Yu-Hsuan Li Liang, Hsuan Su +4
Robust ASR under domain shift is crucial because real-world systems encounter unseen accents and domains with limited labeled data. Although pseudo-labeling offers a practical work…
Investigating Safety Vulnerabilities of Large Audio-Language Models Under Speaker Emotional Variations
Bo-Han Feng, Chien-Feng Liu, Yu-Hsuan Li Liang +9
Large audio-language models (LALMs) extend text-based LLMs with auditory understanding, offering new opportunities for multimodal applications. While their perception, reasoning, a…
EMO-Debias: Benchmarking Gender Debiasing Techniques in Multi-Label Speech Emotion Recognition
Yi-Cheng Lin, Huang-Cheng Chou, Yu-Hsuan Li Liang +1
Speech emotion recognition (SER) systems often exhibit gender bias. However, the effectiveness and robustness of existing debiasing methods in such multi-label scenarios remain und…