4 papers
Summary of DCASE 2026 Task 5: Audio-Dependent Question Answering
Haolin He, Renhe Sun, Zheqi Dai +16
DCASE~2026 Task~5 introduces Audio-Dependent Question Answering (ADQA), which tests whether large audio-language models answer from the audio rather than from textual priors. An Au…
TriA Pipeline: A Large-Scale Automatic Audio Annotation Pipeline For Audio Classification In Specific Scenarios
Hong Lyu, Mingru Yang, Qianhua He +3
There are some datasets of varying scales for audio classification (AC) applied to different tasks. However, annotated data is limited for most scenarios, such as domestic environm…
Measuring Audio's Impact on Correctness: Audio-Contribution-Aware Post-Training of Large Audio Language Models
Haolin He, Xingjian Du, Renhe Sun +16
Large Audio Language Models (LALMs) represent an important frontier in multimodal AI, addressing diverse audio tasks. Recently, post-training of LALMs has received increasing atten…
Generalizable Audio Deepfake Detection via Hierarchical Structure Learning and Feature Whitening in Poincaré sphere
Mingru Yang, Yanmei Gu, Qianhua He +7
Audio deepfake detection (ADD) faces critical generalization challenges due to diverse real-world spoofing attacks and domain variations. However, existing methods primarily rely o…