Very cool way to leverage LLM. Upload your music and see the feedback! 🎸🎸

So amazing.. 🥳🥳🥳

"signal processing meets neural nets" is probably my favourite genre of paper, two great examples: Making Convolutional Networks Shift-Invariant Again by Richard Zhang arxiv.org/abs/1904.11486 Alias-Free Generative Adversarial Networks by Karras et al. arxiv.org/abs/2106.12423

``Towards Generalizability to Tone and Content Variations in the Transcription of Amplifier Rendered Electric Guitar Audio,'' Yu-Hua Chen, Yuan-Chiao Cheng, Yen-Tung Yeh, Jui-Te Wu, Jyh-Shing Roger Jang, Yi-Hsuan Yang, ift.tt/6aOj1pr

Amazing work by Yu-Hua Chen. A very strong guitar transcription model. Go and check demo page to listen the result !

``DiffVox: A Differentiable Model for Capturing and Analysing Professional Effects Distributions,'' Chin-Yun Yu, Marco A. Mart\'inez-Ram\'irez, Junghyun Koo, Ben Hayes, Wei-Hsiang Liao, Gy\"orgy Fazekas, Yuki Mitsufuji, ift.tt/I6Zye2M

When does sampling fail in discrete diffusion models — and how can we fix it? In our work, to appear at #ICLR2025, we show how to improve generation quality from DDMs without additional inference cost, simply by using a better sampling schedule! openreview.net/forum?id=pD6Ti…

I'm pleased to share my internship project Sony AI, DiffVox, a differentiable effects chain for vocals with hundreds of presets. arXiv: arxiv.org/abs/2504.14735 code: github.com/SonyResearch/d… 🤗: huggingface.co/spaces/yoyolic…

``ITO-Master: Inference-Time Optimization for Audio Effects Modeling of Music Mastering Processors,'' Junghyun Koo, Marco A. Martinez-Ramirez, Wei-Hsiang Liao, Giorgio Fabbro, Michele Mancusi, Yuki Mitsufuji, ift.tt/ENPUVqh

❌ We don’t need no negative samples ❌ We don’t need no large batches ❌ No modality gap in the classroom Very happy to introduce SLAP, our latest brick in the wall of multimodal SSL 🎶🧠 Joint work with King @Juj_guinot, accepted at #ISMIR2025! 🇰🇷 1/7

ICML2025: “MuseControlLite” for multifunctional music generation! Better than ControlNet for time-varying conditions while using 6.75 times fewer trainable parameters. Also supports audio infilling! arxiv.org/abs/2506.18729 github.com/fundwotsai2001… musecontrollite.github.io/web/

"Large-Scale Training Data Attribution for Music Generative Models via Unlearning" We explore how machine unlearning can be used for Training Data Attribution (TDA) in large-scale text-to-music diffusion models. 📜 Paper: arxiv.org/abs/2506.18312 Sony AI

🔥Happy to announce that the AI for Music Workshop is coming to #NeurIPS2025! We have an amazing lineup of speakers! We call for papers & demos (due on August 22)! See you in San Diego!🏖️ Chris Donahue Ilaria Manco Akira MAEZAWA Anna Huang McAuley Lab UCSD Zachary Novack NeurIPS Conference

Check out the paper here: arxiv.org/abs/2507.06329 And the website here: mclemcrew.github.io/mixassist-webs… S/O to Ana Marasović for all the leadership, support, and expertise they put into this work! We are so happy with how it turned out and hope it helps the community of music producers!

Qihui Yang, Taylor Berg-Kirkpatrick, Julian McAuley, Zachary Novack, "WildFX: A DAW-Powered Pipeline for In-the-Wild Audio FX Graph Modeling," arxiv.org/abs/2507.10534

We have contributed a late breaking demo paper to ISMIR! By exploiting the compressed information dense latents of Neural Audio Codecs, we can perform zero-shot ‘timbre transfer’ using as little as a single source audio sample for reference. 🔥