AudioSet

~2M 10-second YouTube clips labeled with 600+ audio-event classes.

Papers using AudioSet (25)

Audio-JEPA: Joint-Embedding Predictive Architecture for Audio Representation Learning2025 · 4 citesAaSP: Aliasing-aware Self-Supervised Pre-Training for Audio Spectrogram Transformers2025SAM: A Mamba-2 State-Space Audio-Language Model2025AudioMAE++: learning better masked audio representations with SwiGLU FFNs2025Self-supervised learning method using multiple sampling strategies for general-purpose audio representation2025SoloAudio: Target Sound Extraction with Language-oriented Audio Diffusion Transformer2024Multiscale Audio Spectrogram Transformer for Efficient Audio Classification2023 · 29 citesAudio Mamba: Selective State Spaces for Self-Supervised Audio Representations2024 · 19 citesCMKD: CNN/Transformer-Based Cross-Model Knowledge Distillation for Audio Classification2022 · 17 citesEfficient Training of Audio Transformers with Patchout2021 · 2 citesSSAST: Self-Supervised Audio Spectrogram Transformer2021 · 2 citesEfficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation2022 · 2 citesHTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection2022 · 1 citesMasked Spectrogram Prediction For Self-Supervised Audio Pre-Training2022 · 1 citesAudio Language Modeling using Perceptually-Guided Discrete Representations2022 · 1 citesDynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models2023 · 1 citesEnhancing Zero-shot Audio Classification using Sound Attribute Knowledge from Large Language Models2024 · 1 citesStudy of positional encoding approaches for Audio Spectrogram Transformers2021Conformer-Based Self-Supervised Learning for Non-Speech Audio Tasks2021DECAR: Deep Clustering for learning general-purpose Audio Representations2021AST-SED: An Effective Sound Event Detection Method Based on Audio Spectrogram Transformer2023Improving Self-Supervised Learning for Audio Representations by Feature Diversity and Decorrelation2023Streaming Audio Transformers for Online Audio Tagging2023Efficient Autoregressive Audio Modeling via Next-Scale Prediction2024AxLSTMs: learning self-supervised audio representations with xLSTMs2024