This technical report describes our system for Task 1 of the DCASE 2026 Challenge, which aims to classify heterogeneous audio recordings according to the Broad Sound Taxonomy (BST). The task requires both accurate second-level prediction and consistency with the top-level taxonomy. Our system is built on CLAP-based audio-text representations and is improved along three strategies: expanding the training set with a filtered subset of BSD35k, enhancing acoustic modeling with feature-specific branches, and refining predictions using hierarchy-aware classifiers and KNN-based post-processing. Among the acoustic features considered, the log-STFT branch provides the strongest single-model performance. With KNN-based post-processing, our best single system achieves a hierarchical F1 score (Hier. F1) of 80.84% on the BSD10k-v1.2 set under the same evaluation protocol as the baseline. We further construct ensemble systems by combining models with complementary acoustic features and classification heads, achieving Hier. F1 scores of 81.25% and 81.18%, respectively.
Queen Mary University of London(伦敦玛丽女王大学);HCMC University of Technology(胡志明市理工大学);University of Oxford(牛津大学);Austrian Institute of Technology Vienna(维也纳奥地利技术研究所);Singapore Institute of Technology(新加坡理工学院)
Virufy: A Multi-Branch Deep Learning Network for Automated Detection of COVID-19
Virufy AI Research Group(Virufy AI研究组);University of Alexandria(亚历山大大学);Duke University(杜克大学);University of California San Francisco(加利福尼亚大学旧金山分校);Stanford University(斯坦福大学);University of California Berkeley(加利福尼亚大学伯克利分校)
TLDiffGAN: A Latent Diffusion-GAN Framework with Temporal Information Fusion for Anomalous Sound Detection
Shenzhen International Graduate School, Tsinghua University, China(清华大学深圳国际研究生院);Collaborative Innovation Center for Transport Studies, Dalian Maritime University, China(大连海事大学交通运输协同创新中心)
情感分析主要基于文本,近十年来发展迅速,引起了学术界和工业界的广泛关注。然而,现实世界中的信息通常来自多种形式,如音频和文本。因此,本文基于音频和文本,考虑多模态情感分析的任务,提出了一种新的融合策略,包括多特征融合和多模态融合,以提高音频-文本情感分析的准确性。我们称之为DFF-ATMF(Deep Feature Fusion - Audio and Text Modality Fusion)模型,它由两个并行的分支组成,即基于音频模态的分支和基于文本模态的分支。其核心机制是多特征向量和多通道注意的融合。在CMU-MOSI数据集和最近发布的CMU-MOSEI数据集上的实验,都是从YouTube上收集的情感分析,显示了我们的DFF-ATMF模型非常有竞争力的结果。此外,凭借注意力权重分布热图,我们还证明了使用DFF-ATMF学习的深度特征是互补的,并且是鲁棒的。令人惊讶的是,DFF-ATMF在IEMOCAP数据集上也取得了新的最先进的结果,表明所提出的融合策略对于多模态情感识别也具有良好的泛化能力。
CAD: Conflict-Aware Decoding to Mitigate Cross-Modal Hallucinations in Omnimodal Large Language Models
Tsinghua Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院);Pengcheng Laboratory(鹏城实验室);School of Cyber Science and Engineering, Zhengzhou University(郑州大学网络空间安全学院)
SALM: Spatial Audio Language Model with Structured Embeddings for Understanding and Editing
Institute of Acoustics, Chinese Academy of Sciences, China(中国科学院声学研究所);MiLM Plus, Xiaomi Inc., China(小米公司);Xi’an Jiaotong Liverpool University, China(西安交通大学利物浦大学);University of Chinese Academy of Sciences, China(中国科学院大学)
Self Training and Ensembling Frequency Dependent Networks with Coarse Prediction Pooling and Sound Event Bounding Boxes
Institute of Civil Military Technology Cooperation(军民技术合作研究所);Defense Acquisition Program Administration(国防采计局);Ministry of Trade, Industry and Energy(产业通商资源部);Korea Research Institute of Ships and Ocean engineering(韩国船舶海洋工程研究院);Ministry of Oceans and Fisheries(海洋水产部)
Classification of Infant Sleep/Wake States: Cross-Attention among Large Scale Pretrained Transformer Networks using Audio, ECG, and IMU Data
University of Illinois at Urbana Champaign(伊利诺伊大学厄巴纳-香槟分校);Beckman Institute for Advanced Science and Technology(贝克曼高级科学技术研究院);Worcester Polytechnic Institute(伍斯特理工学院)
Improving Perceptual Audio Aesthetic Assessment via Triplet Loss and Self-Supervised Embeddings
Research Center for Information Technology Innovation, Academia Sinica(学术院信息科技创新研究中心);College of Informatics, National Chengchi University(国立成功大学资讯学院);Institute of Information Science, Academia Sinica(学术院信息科学研究所);Institute of Communications Engineering, National Yang Ming Chiao Tung University(国立阳明交通大学通讯工程研究所)
STFTCodec: High-Fidelity Audio Compression through Time-Frequency Domain Representation
Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院);International Digital Economy Academy (IDEA)(国际数字经济学院(IDEA));Shenzhen Graduate School, Peking University(北京大学深圳研究生院)
Positive Sample Propagation along the Audio-Visual Event Line
Hefei University of Technology(合肥工业大学);Intelligent Interconnected Systems Laboratory of Anhui Province(安徽省智能互联系统实验室);Australian National University(澳大利亚国立大学)
Talker-T2AV: Joint Talking Audio-Video Generation with Autoregressive Diffusion Modeling
Hong Kong University of Science and Technology(香港科学与技术大学);Zhejiang University(浙江大学);National University of Singapore(新加坡国立大学);The Chinese University of Hong Kong(香港中文大学);Peking University(北京大学);Independent Researcher(独立研究者)
STAR-Bench: Probing Deep Spatio-Temporal Reasoning as Audio 4D Intelligence
Fudan University(复旦大学);Shanghai AI Laboratory(上海人工智能实验室);The Chinese University of Hong Kong(香港中文大学);Shanghai Innovation Institute(上海创新研究院);Beihang University(北京航空航天大学);Shanghai Jiao Tong University(上海交通大学)
Representing Speech Through Autoregressive Prediction of Cochlear Tokens
Department of Brain;Cognitive Sciences \& McGovern Institute for Brain Research;Department of Computer Science \& Wu Tsai Neurosciences Institute;Department of Psychology
Semantic-Aware Implicit Neural Audio-Driven Video Portrait Generation
The Chinese University of Hong Kong(香港中文大学);Monash University(莫纳什大学);SenseTime Research(商汤科技研究院);Sensetime(商汤科技(此处原英文为“sensetime”,结合上下文“wuwenyan@sensetime.com”推测为“商汤科技”,但严格按“机构粒度”提取,原文本中“SenseTime Research”已单独列出,此处“sensetime”视为同一机构))