mlsanityData to 14 Oct 2026

Woosh: A Sound Effects Foundation Model

arXiv 2604.01929 ↗First posted 2 Apr 2026cs.SD cs.AI cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

The audio research community depends on open generative models as foundational tools for building novel approaches and establishing baselines. In this report, we present Woosh, Sony AI's publicly released sound effect foundation model, detailing its architecture, training process, and an evaluation against other popular open models. Being optimized for sound effects, we provide (1) a high-quality audio encoder/decoder model and (2) a text-audio alignment model for conditioning, together with (3) text-to-audio and (4) video-to-audio generative models. Distilled text-to-audio and video-to-audio models are also included in the release, allowing for low-resource operation and fast inference. Our evaluation on both public and private data shows competitive or better performance for each module when compared to existing open alternatives like StableAudio-Open and TangoFlux. Inference code and model weights are available at https://github.com/SonyResearch/Woosh. Demo samples can be found at https://sonyresearch.github.io/Woosh/.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 40 of its 47 references that are in the map. First posted on arXiv 2 Apr 2026.

Builds on

40 of 47 references.

References · 40

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  4. 2022Classifier-Free Diffusion Guidancecited by 5,847
  5. 2022Flow Matching for Generative Modelingcited by 5,702
  6. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  7. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,300
  8. 2023ImageBind: One Embedding Space To Bind Them Allcited by 1,175
  9. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,154
  10. 2025FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Spacecited by 1,006
  11. 2016Least Squares Generative Adversarial Networkscited by 1,001
  12. 2021SoundStream: An End-to-End Neural Audio Codeccited by 771
28 more
  1. 2022Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentationcited by 719
  2. 2022High Fidelity Neural Audio Compressioncited by 687
  3. 2020VGGSound: A Large-scale Audio-Visual Datasetcited by 648
  4. 2023AudioLDM: Text-to-Audio Generation with Latent Diffusion Modelscited by 599
  5. 2025Mean Flows for One-step Generative Modelingcited by 561
  6. 2025Qwen3-Omni Technical Reportcited by 497
  7. 2023Simple and Controllable Music Generationcited by 488
  8. 2023MusicLM: Generating Music From Textcited by 448
  9. 2023High-Fidelity Audio Compression with Improved RVQGANcited by 431
  10. 2023AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretrainingcited by 344
  11. 2024Flow Matching Guide and Codecited by 301
  12. 2022AudioGen: Textually Guided Audio Generationcited by 295
  13. 2024Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillationcited by 279
  14. 2023WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Researchcited by 267
  15. 2021Efficient Training of Audio Transformers with Patchoutcited by 226
  16. 2024Fast Timing-Conditioned Latent Audio Diffusioncited by 181
  17. 2022HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detectioncited by 176
  18. 2023Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesiscited by 153
  19. 2024MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesiscited by 134
  20. 2024GameGen-X: Interactive Open-world Game Video Generationcited by 128
  21. 2024Synchformer: Efficient Synchronization from Sparse Cuescited by 97
  22. 2024Long-form music generation with latent diffusioncited by 89
  23. 2025SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillationcited by 87
  24. 2024TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching and Clap-Ranked Preference Optimizationcited by 68
  25. 2022Full-band General Audio Synthesis with Score-based Diffusioncited by 32
  26. 2020Upsampling artifacts in neural audio synthesiscited by 28
  27. 2025FoleyBench: A Benchmark For Video-to-Audio Modelscited by 7
  28. 2025SoundReactor: Frame-level Online Video-to-Audio Generationcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Stable Audio 3cited by 6
  2. 2026AudioX-Turbo: A Unified Framework for Efficient Anything-to-Audio Generationcited by 1
  3. 2026SonicCaps: Large-Scale Diverse and Fine-Grained Captioning for Improved Audio-Retrievalcited by 0
  4. 2026SCAPES: Semantically Conditioned Autoregressive Prior for Environmental Soundscited by 0