mlsanityData to 14 Oct 2026

The Benefit Of Temporally-Strong Labels In Audio Event Classification

arXiv 2105.07031 ↗First posted 14 May 2021cs.SD eess.AScited by 83

Not on the map. Why?

Abstract (arXiv)

To reveal the importance of temporal precision in ground truth audio event labels, we collected precise (~0.1 sec resolution) "strong" labels for a portion of the AudioSet dataset. We devised a temporally strong evaluation set (including explicit negatives of varying difficulty) and a small strong-labeled training subset of 67k clips (compared to the original dataset's 1.8M clips labeled at 10 sec resolution). We show that fine-tuning with a mix of weak and strongly labeled data can substantially improve classifier performance, even when evaluated using only the original weak labels. For a ResNet50 architecture, d' on the strong evaluation data including explicit negatives improves from 1.13 to 1.41. The new labels are available as an update to AudioSet.

Key facts. Cited by 83 papers in the map (data through 14 Oct 2026). First posted on arXiv 14 May 2021.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 3; 2022: 6; 2023: 10; 2024: 19; 2025: 28; 2026: 17.

83 papers.

Sort:

By area:

  1. 2024MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmarkcited by 288
  2. 2022Masked Autoencoders that Listencited by 273
  3. 2023WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Researchcited by 267
  4. 2024Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilitiescited by 186
  5. 2022HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detectioncited by 176
  6. 2025Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilitiescited by 133
  7. 2024FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Soundscited by 110
  8. 2023Joint Audio and Speech Understandingcited by 100
  9. 2022MAViL: Masked Audio-Video Learnerscited by 59
  10. 2024AVHBench: A Cross-Modal Hallucination Benchmark for Audio-Visual Large Language Modelscited by 56
  11. 2024Auffusion: Leveraging the Power of Diffusion and Large Language Models for Text-to-Audio Generationcited by 54
  12. 2023A-JEPA: Joint-Embedding Predictive Architecture Can Listencited by 53
38 more
  1. 2023Epic-Sounds: A Large-scale Dataset of Actions That Soundcited by 47
  2. 2023CompA: Addressing the Gap in Compositional Reasoning in Audio-Language Modelscited by 43
  3. 2025ThinkSound: Chain-of-Thought Reasoning in Multimodal Large Language Models for Audio Generation and Editingcited by 34
  4. 2024EzAudio: Enhancing Text-to-Audio Generation with Efficient Diffusion Transformercited by 31
  5. 2021Zero-shot Audio Source Separation through Query-based Learning from Weakly-labeled Datacited by 27
  6. 2025AudioX: A Unified Framework for Anything-to-Audio Generationcited by 27
  7. 2025UniForm: A Unified Multi-Task Diffusion Transformer for Audio-Video Generationcited by 22
  8. 2025FreeAudio: Training-Free Timing Planning for Controllable Long-Form Text-to-Audio Generationcited by 21
  9. 2023Audio Generation with Multiple Conditional Diffusion Modelcited by 18
  10. 2025MeanAudio: Fast and Faithful Text-to-Audio Generation with Mean Flowscited by 14
  11. 2025Pushing the Frontier of Audiovisual Perception with Large-Scale Multimodal Correspondence Learningcited by 13
  12. 2026Audio-Omni: Extending Multi-modal Understanding to Versatile Audio Generation and Editingcited by 12
  13. 2024DRCap: Decoding CLAP Latents with Retrieval-Augmented Generation for Zero-shot Audio Captioningcited by 11
  14. 2025ControlAudio: Tackling Text-Guided, Timing-Indicated and Intelligible Audio Generation via Progressive Diffusion Modelingcited by 11
  15. 2021You Only Hear Once: A YOLO-like Algorithm for Audio Segmentation and Sound Event Detectioncited by 10
  16. 2023AnuraSet: A dataset for benchmarking Neotropical anuran calls identification in passive acoustic monitoringcited by 10
  17. 2024Enhancing Low-Resource Language and Instruction Following Capabilities of Audio Language Modelscited by 10
  18. 2023A Whisper transformer for audio captioning trained with synthetic captions and transfer learningcited by 9
  19. 2025TACOS: Temporally-aligned Audio CaptiOnS for Language-Audio Pretrainingcited by 9
  20. 2025Detect Any Sound: Open-Vocabulary Sound Event Detection with Multi-Modal Queriescited by 9
  21. 2022Filler Word Detection and Classification: A Dataset and Benchmarkcited by 7
  22. 2024Audio Dialogues: Dialogues dataset for audio and music understandingcited by 7
  23. 2025WAVE: Learning Unified & Versatile Audio-Visual Embeddings with Multimodal LLMcited by 7
  24. 2023Advancing Natural-Language Based Audio Retrieval with PaSST and Large Audio-Caption Data Setscited by 6
  25. 2024Enhancing Temporal Understanding in Audio Question Answering for Large Audio Language Modelscited by 5
  26. 2025Generative Audio Language Modeling with Continuous-valued Tokens and Masked Next-Token Predictioncited by 5
  27. 2026Logics-Parsing-Omni Technical Reportcited by 5
  28. 2021The impact of non-target events in synthetic soundscapes for sound event detectioncited by 4
  29. 2022SEED: Sound Event Early Detection via Evidential Uncertaintycited by 4
  30. 2024From Weak to Strong Sound Event Labels using Adaptive Change-Point Detection and Active Learningcited by 4
  31. 2024OMCAT: Omni Context Aware Transformercited by 4
  32. 2024Do Audio-Language Models Understand Linguistic Variations?cited by 4
  33. 2025FlexSED: Towards Open-Vocabulary Sound Event Detectioncited by 4
  34. 2025SAO-Instruct: Free-form Audio Editing using Natural Language Instructionscited by 4
  35. 2025Revisiting Audio-language Pretraining for Learning General-purpose Audio Representationcited by 4
  36. 2024Prototype based Masked Audio Model for Self-Supervised Learning of Sound Event Detectioncited by 3
  37. 2024Smooth-Foley: Creating Continuous Sound for Video-to-Audio Generation Under Semantic Guidancecited by 3
  38. 2025CASTELLA: Long Audio Dataset with Captions and Temporal Boundariescited by 3

50 most cited of 83 All 83 (JSON)