Few-Shot Audio Classification

Ask about this topic

Overview

Few-shot audio classification studies how to recognize new sound categories when labeled examples are scarce, across tasks such as speech, environmental sound, music, and medical audio. Common approaches reuse pretrained audio embeddings from models such as HuBERT, wav2vec 2.0, and CLAP, then adapt them with prototypes, lightweight classifiers, prompts, or meta-learning. Researchers also study open-set rejection and class-incremental learning, where systems must identify unknown sounds or add classes without forgetting earlier ones. A central challenge is that strong results on standard episodic benchmarks may not hold under domain shifts or changed background cues, while deeper adaptation can improve accuracy at the cost of data, compute, or transfer to unseen classes.

Latest papers

CardsList

18 papers2 papers in the last four weeks, down 33% on the four weeks before. 0.0% of all new papers.

  1. DF-PALM: Dynamic Fusion Prompt Learning for Audio--Language Models

    Oct 18, 2026Yulin Sun, Shenghua Li, Yong Dou +3Few-Shot Audio ClassificationPrompt Learning

    College of Computer Science and Technology, National University of Defense Technology, Changsha, China. · State Key Laboratory of Complex & Critical Software Environment

  2. Extending Music Annotation Schemas: Zero-Shot Prediction or Few-Shot Adaptation?

    Oct 2, 2026Christos Plachouras, Emmanouil Benetos, Johan PauwelsMusic Information RetrievalAudio-Language Model Evaluation

    School of Electronic Engineering and Computer Science, Queen Mary University of London, UK

  3. ToneCL: Contrastive Learning for Few-Shot Syllable-Level Tone Classification

    Sep 21, 2026Qisheng Liao, Youngah DoContrastive LearningFew-Shot Audio Classification

    Department of Linguistics The University of Hong Kong

  4. Sample-Conditioned Representation Selection for Audio Few-Shot Learning

    Sep 15, 2026Fengrui Liu, Ningxin Shen, Yi Li +3Few-Shot Audio ClassificationAudio Representation Learning

    National Key Laboratory of Space Integrated Information System, Institute of Software, Chinese Academy of Sciences · School of Computer Science, Nanjing University · School of Computer Science and Technology, East China Normal University +1

  5. Comparing Self-Supervised and Domain-Invariant Features for Cross-Domain Voice Phishing Detection

    Sep 7, 2026Jeongmin Lee, Seung Yun, Minkyu Lee +3Domain GeneralizationSelf-Supervised Speech Representation Learning

    Electronics and Telecommunications Research Institute, Daejeon, Korea · University of Science and Technology, Daejeon, Korea

  6. SPECTRA: Subspace-Preserving Embedding Calibration, Transport, and Replay for Fully Few-Shot Class-Incremental Audio Classification

    Aug 25, 2026Giries Abu Ayoub, Loay Mualem, Simon KormanFew-Shot Audio ClassificationContinual Learning

    Department of Computer Science, University of Haifa · Institute for AI, University of Stuttgart · IMPRS-IS

  7. A Parameter-Free Few-Shot Evaluation for Elephant Vocalisation Classification

    Aug 14, 2026Christiaan M. Geldenhuys, Thomas R. NieslerFew-Shot Audio ClassificationPrototype-Based Classification

    Department of Electrical and Electronic Engineering University of Stellenbosch

  8. Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement

    Jul 29, 2026Tianyan Deng, Yanxiong Li, Rui Gao +1Few-Shot Audio ClassificationPrototype-Based Classification

    School of Mathematics South China University of Technology Guangzhou, China · School of Electronic and Information Engineering South China University of Technology Guangzhou, China

  9. Few-Shot Open-Set Audio Classification Using Attention Information-Fused Prototypes

    Jul 1, 2026Yanxiong Li, Jiaxin Tan, Qianqian Li +3Few-Shot Audio ClassificationPrototype-Based Classification

    School of Electronic and Information Engineering, South China University of Technology, Guangzhou 510640, China · Faculty of Information Technology and Communication Sciences, Tampere University, FI-33720 Tampere, Finland

  10. Unlocking In-Context Learning in Audio-Language Models from Decentralized Medical Audio

    Jun 22, 2026Ran Piao, Tsai-Ning Wang, Martijn den Dekker +4Few-Shot Audio ClassificationMultimodal ICL

    Eindhoven University of Technology, The Netherlands · Erasmus MC, The Netherlands · Rijnstate Hospital, The Netherlands +1

  11. SubT: Subspace Tuning for Few-shot Generalization of Audio-Language Models

    Jun 17, 2026Jaehyuk Jang, Kangwook Ko, Wonjun Lee +1Few-Shot Audio ClassificationZero-Shot Learning

    KAIST

  12. Transductive Zero-Shot Audio Classification with Audio-Language Models

    Jun 15, 2026Jingwen Zhou, Mingzhe WangAudio-Language Model EvaluationFew-Shot Audio Classification

    Xidian University, Xi’an, China

  13. Acoustic Prompting via Stage-wise Modulation for Few-Shot Learning in Audio Language Models

    Jun 14, 2026Hyebin Cho, Jaehyuk Jang, Changick Kim +1Few-Shot Audio ClassificationAudio Representation Learning

    Korea Advanced Institute of Science and Technology, South Korea

  14. Few-shot Class-variable Incremental Audio Classification via Prototype Adaptation and Pseudo Class-variable Training

    Jun 8, 2026Yanxiong Li, Guoqing Chen, Qianqian Li +1Class-Incremental LearningFew-Shot Audio Classification

    School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China

  15. Drift-Augmented Scoring: Text-Derived Noise Robustness for Zero-Shot Audio-Language Classification

    Jun 3, 2026Tu Vo, Sheir Zaheer, Chan Y. ParkFew-Shot Audio ClassificationAudio Understanding

    KC Machine Learning Lab

  16. SpurAudio: A Benchmark for Studying Shortcut Learning in Few-Shot Audio Classification

    May 13, 2026Giries Abu Ayoub, Morad Tukan, Loay MualemFew-Shot Audio ClassificationAudio Understanding

    Independent Researcher · University of Stuttgart, Germany · IMPRS-IS, Germany

  17. Scaling few-shot spoken word classification with generative meta-continual learning

    May 13, 2026Louise Beyers, Batsirayi Mupamhi Ziki, Ruan van der MerweFew-Shot Audio ClassificationContinual Learning

    Bytefuse

  18. Few-Shot Contrastive Adaptation for Audio Abuse Detection in Low-Resource Indic Languages

    Apr 10, 2026Aditya Narayan Sankaran, Reza Farahbakhsh, Noel CrespiHate Speech DetectionLow-Resource Language Processing

    SAMOVAR, Télécom SudParis Institut Polytechnique de Paris 91120 Palaiseau, France