11 papers
Overview of ESDD2: Environment-Aware Speech and Sound Deepfake Detection Challenge
Xueping Zhang, Han Yin, Yang Xiao +4
The Environment-Aware Speech and Sound Deepfake Detection Challenge (ESDD2), held in conjunction with ICME 2026, evaluated systems for five component-level audio spoofing detection…
A Multi-Stage Separation-and-Classification Framework Guided by Complementary Acoustic-to-Semantic Clues
Younghoo Kwon, Junwoo Park, Han Yin +1
This report describes the system proposed for the DCASE 2026 Challenge Task 4: Spatial Semantic Segmentation of Sound Scenes (S5). Specifically, we develop a multi-stage framework…
AudioDER: A Deduplication-Enhanced Reasoning Dataset for Post-Training Large Audio-Language Models
Hui Geng, Yi Su, Zijian Gao +5
Recent advances in pretrained large audio-language models (LALMs) have demonstrated strong capabilities across speech, sound, and music. To adapt these models to downstream tasks w…
Why Can't They Remember? Uncovering Representation and Retrieval Bottlenecks in Multi-Turn Acoustic Memory
Yang Xiao, Siyi Wang, Han Yin +4
Large audio language models (LALMs) process both speech and environmental acoustic cues, yet struggle to retain non-speech information across multi-turn interactions. The performan…
PolyBench: A Benchmark for Compositional Reasoning in Polyphonic Audio
Yuanjian Chen, Yang Xiao, Han Yin +3
Large Audio Language Models (LALMs) are increasingly capable of reasoning over audio, yet existing benchmarks offer limited coverage of reasoning in polyphonic audio, where multipl…
The First Environmental Sound Deepfake Detection Challenge: Benchmarking Robustness, Evaluation, and Insights
Han Yin, Yang Xiao, Rohan Kumar Das +2
Recent progress in audio generation has made it increasingly easy to create highly realistic environmental soundscapes, which can be misused to produce deceptive content, such as f…
Focus Then Listen: An Empirical Study of Plug-and-Play Audio Enhancer for Noise-Robust Large Audio Language Models
Han Yin, Yang Xiao, Younghoo Kwon +2
Large audio language models (LALMs) are a class of foundation models for audio understanding. Existing LALMs tend to degrade significantly in real-world noisy acoustic conditions w…
ASCMamba: Multimodal Time-Frequency Mamba for Acoustic Scene Classification
Bochao Sun, Dong Wang, ZhanLong Yang +2
Acoustic Scene Classification (ASC) is a fundamental problem in computational audition, which seeks to classify environments based on the distinctive acoustic features. In the ASC…
Noise-Robust Sound Event Detection and Counting via Language-Queried Sound Separation
Yuanjian Chen, Yang Xiao, Han Yin +2
Most sound event detection (SED) systems perform well on clean datasets but degrade significantly in noisy environments. Language-queried audio source separation (LASS) models show…
Ensemble Confidence Calibration for Sound Event Detection in Open-environment
Yuanjian Chen, Han Yin
Sound event detection (SED) has made strong progress in controlled environments with clear event categories. However, real-world applications often take place in open environments.…
Enhancing Stereo Sound Event Detection with BiMamba and Pretrained PSELDnet
Wenmiao Gao, Han Yin
Pre-training methods have greatly improved the performance of sound event localization and detection (SELD). However, existing Transformer-based models still face high computationa…