Recent Large Audio Language Models (LALMs) excel in understanding but often lack transparent reasoning. To address this "black-box" limitation, we organized the Audio Reasoning Challenge at Interspeech 2026, the first shared task dedicated to evaluating Chain-of-Thought (CoT) quality in the audio domain. The challenge introduced MMAR-Rubrics, a novel instance-level protocol assessing the factuality and logic of reasoning chains. Featured Single Model and Agent tracks, the competition attracting 156 teams from 18 countries and regions. Results show agent systems currently lead in reasoning quality, utilizing iterative tool orchestration and cross-modal analysis. Besides, single models are rapidly advancing via reinforcement learning and sophisticated data pipeline. We details the challenge design, methodology, and a comprehensive analysis of state-of-the-art systems, providing new insights for explainable audio intelligence.
The Interspeech 2026 Audio Encoder Capability Challenge for Large Audio Language Models
MiLM Plus, Xiaomi Inc., Beijing, China(小米公司,北京);DataoceanAI Inc., USA(DataoceanAI公司,美国);Centre for Vision Speech and Signal Processing, University of Surrey, Guildford, UK(视觉语音与信号处理中心, Surrey大学, Guildford,英国);Shenzhen International Graduate School, Tsinghua University, Shenzhen, China(深圳国际研究生院,清华大学,深圳,中国)
IQRA 2026: Interspeech Challenge on Automatic Pronunciation Assessment for Modern Standard Arabic (MSA)
DFKI(德国人工智能研究中心);Technical University of Berlin(柏林工业大学);University of Sheffield(谢菲尔德大学);University of New South Wales(新南威尔士大学);Alexandria University(亚历山大大学);QCRI(卡塔尔计算研究所);Taibah University(塔伊巴大学);HUMAIN
Evaluating robustness of You Only Hear Once(YOHO) Algorithm on noisy audios in the VOICe Dataset
Manipal Institute of Technology(曼尼帕尔理工学院)
机器监听中的声音事件检测(SED)需要识别音频文件中的不同声音并识别音频中特定声音事件的开始和结束时间。SED可用于各种应用,例如音频监视、语音识别以及多媒体数据库中的数据的基于上下文的索引和检索。然而,在现实生活中,来自各种来源的音频很少没有任何干扰噪声或干扰。在本文中,我们测试的性能,你只听到一次(YOHO)算法对嘈杂的音频数据。受计算机视觉中You Only Look Once(YOLO)算法的启发,YOHO算法可以在音乐语音检测数据集、TUT声音事件和Urban-SED数据集等数据集上与各种最先进算法的性能相匹配,但推理时间更短。在本文中,我们探讨了YOHO算法的VOICe数据集上的性能,包含在不同的声音噪声比(SNR)的噪声的音频文件。YOHO可以超越或至少匹配VOICe数据集论文中报告的最佳性能SED算法,并在更短的时间内进行推断。
ChronosAudio: A Comprehensive Long-Audio Benchmark for Evaluating Audio-Large Language Models
Nanyang Technological University(南洋理工大学);Independent Researcher(独立研究者);United Arab Emirates University(阿联酋大学);North China Electric Power University(华北电力大学);Southwest Jiaotong University(西南交通大学);Squirrel AI Learning(Squirrel AI学习)
Hearing is Believing? Evaluating and Analyzing Audio Language Model Sycophancy with SYAUDIO
University of Electronic Science and Technology of China(电子科技大学);Mohamed bin Zayed University of Artificial Intelligence(Mohamed bin Zayed人工智能大学);King Abdullah University of Science and Technology(卡布斯大学);Georgia Institute of Technology(佐治亚理工学院)
Beyond Accuracy: ARIA-Rubrics for Evaluating Audio Reasoning in Large Audio Language Models
Imperial College London(帝国理工学院);Technische Universität München(慕尼黑工业大学);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学);Shanghai Jiao Tong University(上海交通大学);Johns Hopkins University(约翰斯·霍普金斯大学)
Words at Play: Benchmarking Audio Pun Understanding in Large Audio-Language Models
School of Computer Science, University of Auckland(奥克兰大学计算机科学学院);Singapore University of Technology and Design(新加坡科技设计大学);School of Electronic Engineering and Computer Science, Queen Mary University of London(伦敦大学玛丽女王学院电子工程与计算机科学学院);School of Statistics and Data Science, Nankai University(南开大学统计与数据科学学院)
Enhancing Speech Emotion Recognition with Graph-Based Multimodal Fusion and Prosodic Features for the Speech Emotion Recognition in Naturalistic Conditions Challenge at Interspeech 2025
Federal University of Goiás(戈亚斯联邦大学);Federal University of Rio Grande do Norte(北里奥格兰德联邦大学);Aeronautics Institute of Technology(航空技术研究所);Federal University of Mato Grosso(马托格罗索联邦大学)
本文面向 INTERSPEECH 2025 自然条件语音情感识别挑战赛,提出结合先进音频模型、韵律与频谱增强文本特征、F0 量化和集成学习的鲁棒系统,并验证图注意力网络融合有效性,测试集 Macro F1 达 39.79%。
The Interspeech 2024 Challenge on Speech Processing Using Discrete Units
Carnegie Mellon University(卡内基梅隆大学);The Hebrew University of Jerusalem(耶路撒冷希伯来大学);Shanghai Jiao Tong University(上海交通大学);Renmin University of China(中国人民大学)
The Multimodal Information Based Speech Processing (MISP) 2025 Challenge: Audio-Visual Diarization and Recognition
University of Science and Technology of China(中国科学技术大学);Georgia Institute of Technology(佐治亚理工学院);Carnegie Mellon University(卡内基梅隆大学);Northwestern Polytechnical University(西北工业大学);University of Palermo(巴勒莫大学);Delft University of Technology(代尔夫特理工大学)
Evaluating Off-the-Shelf Machine Listening and Natural Language Models for Automated Audio Captioning
Huawei Technologies, Munich Research Center(华为技术有限公司慕尼黑研究中心);Music Technology Group, Universitat Pompeu Fabra(庞培法布拉大学音乐技术研究组);Audio Research Group, Tampere University(坦佩雷大学音频研究组)