mlsanityData to 14 Oct 2026

PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition

arXiv 1912.10211 ↗First posted 21 Dec 2019cs.SD eess.AScited by 574

Not on the map. Why?

Cited by 53 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Audio pattern recognition is an important research topic in the machine learning area, and includes several tasks such as audio tagging, acoustic scene classification, music classification, speech emotion classification and sound event detection. Recently, neural networks have been applied to tackle audio pattern recognition problems. However, previous systems are built on specific datasets with limited durations. Recently, in computer vision and natural language processing, systems pretrained on large-scale datasets have generalized well to several tasks. However, there is limited research on pretraining systems on large-scale datasets for audio pattern recognition. In this paper, we propose pretrained audio neural networks (PANNs) trained on the large-scale AudioSet dataset. These PANNs are transferred to other audio related tasks. We investigate the performance and computational complexity of PANNs modeled by a variety of convolutional neural networks. We propose an architecture called Wavegram-Logmel-CNN using both log-mel spectrogram and waveform as input feature. Our best PANN system achieves a state-of-the-art mean average precision (mAP) of 0.439 on AudioSet tagging, outperforming the best previous system of 0.392. We transfer PANNs to six audio pattern recognition tasks, and demonstrate state-of-the-art performance in several of those tasks. We have released the source code and pretrained models of PANNs: https://github.com/qiuqiangkong/audioset_tagging_cnn.

Key facts. Cited by 574 papers in the map (data through 14 Oct 2026). First posted on arXiv 21 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 45; 2022: 75; 2023: 95; 2024: 118; 2025: 130; 2026: 111.

574 papers.

Sort:

By area:

  1. 2021Perceiver: General Perception with Iterative Attentioncited by 1,104
  2. 2021AST: Audio Spectrogram Transformercited by 643
  3. 2023AudioLDM: Text-to-Audio Generation with Latent Diffusion Modelscited by 599
  4. 2021VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Textcited by 429
  5. 2022BEATs: Audio Pre-Training with Acoustic Tokenizerscited by 388
  6. 2022Masked Autoencoders that Listencited by 273
  7. 2023WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Researchcited by 267
  8. 2021Efficient Training of Audio Transformers with Patchoutcited by 226
  9. 2024Stable Audio Opencited by 197
  10. 2024Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilitiescited by 186
  11. 2022HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detectioncited by 176
  12. 2023Query-Dependent Video Representation for Moment Retrieval and Highlight Detectioncited by 166
38 more
  1. 2022Dawn of the transformer era in speech emotion recognition: closing the valence gapcited by 157
  2. 2022UMT: Unified Multi-modal Transformers for Joint Video Moment Retrieval and Highlight Detectioncited by 148
  3. 2022Contrastive Audio-Visual Masked Autoencodercited by 146
  4. 2023Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Modelscited by 134
  5. 2024MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesiscited by 134
  6. 2024FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMscited by 122
  7. 2023Audiobox: Unified Audio Generation with Natural Language Promptscited by 120
  8. 2023ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalitiescited by 118
  9. 2021Broaden Your Views for Self-Supervised Video Learningcited by 108
  10. 2023Mustango: Toward Controllable Text-to-Music Generationcited by 100
  11. 2023MusicLDM: Enhancing Novelty in Text-to-Music Generation Using Beat-Synchronous Mixup Strategiescited by 94
  12. 2023Make-An-Audio 2: Temporal-Enhanced Text-to-Audio Generationcited by 90
  13. 2021Pano-AVQA: Grounded Audio-Visual Question Answering on 360^circ Videoscited by 86
  14. 2023AUDIT: Audio Editing by Following Instructions with Latent Diffusion Modelscited by 83
  15. 2025Step-Audio: Unified Understanding and Generation in Intelligent Speech Interactioncited by 83
  16. 2025Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generationcited by 83
  17. 2021PSLA: Improving Audio Tagging with Pretraining, Sampling, Labeling, and Aggregationcited by 82
  18. 2022HEAR: Holistic Evaluation of Audio Representationscited by 78
  19. 2023Mousai: Text-to-Music Generation with Long-Context Latent Diffusioncited by 78
  20. 2024Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Modelcited by 72
  21. 2021LEAF: A Learnable Frontend for Audio Classificationcited by 69
  22. 2023V2A-Mapper: A Lightweight Solution for Vision-to-Audio Generation by Connecting Foundation Modelscited by 65
  23. 2023UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognitioncited by 64
  24. 2022Vocalsound: A Dataset for Improving Human Vocal Sounds Recognitioncited by 62
  25. 2025UniVerse-1: Unified Audio-Video Generation via Stitching of Expertscited by 61
  26. 2022MAViL: Masked Audio-Video Learnerscited by 59
  27. 2024TR-DETR: Task-Reciprocal Transformer for Joint Moment Retrieval and Highlight Detectioncited by 59
  28. 2023MomentDiff: Generative Video Moment Retrieval from Random to Realcited by 58
  29. 2021Audio Captioning Transformercited by 55
  30. 2024Auffusion: Leveraging the Power of Diffusion and Large Language Models for Text-to-Audio Generationcited by 54
  31. 2021Distilling Audio-Visual Knowledge by Compositional Contrastive Learningcited by 53
  32. 2021PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognitioncited by 53
  33. 2023A-JEPA: Joint-Embedding Predictive Architecture Can Listencited by 53
  34. 2024EAT: Self-Supervised Pre-Training with Efficient Audio Transformercited by 53
  35. 2023Efficient Neural Music Generationcited by 50
  36. 2025HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generationcited by 46
  37. 2023CoMoSpeech: One-Step Speech and Singing Voice Synthesis via Consistency Modelcited by 45
  38. 2023UnIVAL: Unified Model for Image, Video, Audio and Language Taskscited by 45

50 most cited of 574 All 574 (JSON)