Hao Hao Tan
@GoodGood014AI/ML @BandLab. ex @tiktok_us @sutdsg. Machine learning & music tech. 🇲🇾 🇸🇬
Similar User
@carlthome
@deeplearnmusic
@latentspaces
@umpedronosapato
@_emir_demirel_
@csteinmetz1
@napulen
@affige_yang
@QiuqiangK
@mfu3ntes
@jordiponsdotme
@elio_elioo
@Ilaria__Manco
@di_bogdanov
@NicholasJBryan
If you’re a Member, we’ve also added some serious Studio upgrades. Build on your MIDI ideas quickly with Smart Tools, and give your ideas that extra push with Extend, Layer, and Recompose! 🦾 (3/5)
MIDI Smart Tools is finally out on BandLab! Think of it as MS Copilot, but in the context of a music DAW. Heavily involved in this with my teammates 😀🎶
Wanna see how far your creativity can go with this AI-powered trio? Peep this tutorial to discover new ways to create with Smart Tools! 🔧 blog.bandlab.com/smart-tools-ba… (5/5)
🧮 Just finished writing a new blog post on RVC, one of the most popular voice conversion project on GitHub: gudgud96.github.io/2024/09/26/ann… If you are interested in Fake Drake & AI covers, and want to dive a little bit deeper on the technical details, I hope this article is for you.
"More AI to come" to sports, from F1 racing to Premier League football: youtube.com/watch?v=A_pxpJ…
Today, we release several Moshi artifacts: a long technical report with all the details behind our model, weights for Moshi and its Mimi codec, along with streaming inference code in Pytorch, Rust and MLX. More details below 🧵 ⬇️ Paper: kyutai.org/Moshi.pdf Repo:…
Audio Match Cutting Finding and Creating Matching Audio Transitions in Movies and Videos discuss: huggingface.co/papers/2408.10… A "match cut" is a common video editing technique where a pair of shots that have a similar composition transition fluidly from one to another. Although…
🥳We just uploaded another ISMIR paper to arXiv: Stem-JEPA: A Joint-Embedding Predictive Architecture for Musical Stem Compatibility Estimation A. Riou, S. Lattner, G. Hadjeres, M. Anslow, G. Peeters 📜 Paper: arxiv.org/abs/2408.02514 🌍 Code: github.com/SonyCSLParis/S… For more…
Glad to announce that Stem-JEPA has been accepted to @ISMIRConf ! In this work, we tackle the task of musical stem compatibility estimation (what “fits” together) as a representation learning problem. (1/7) Paper: arxiv.org/abs/2408.02514 Code: github.com/SonyCSLParis/S…
I gave a 1-hour talk about generative modelling at the EEML 2024 summer school last month. It's mostly an intuitive look at how and why diffusion models actually work -- not unlike the content of my recent blog posts. All summer school talks will be freely available online!🙏
EEML'24 Day 1 videos are out! 🇷🇸 * Intro to DL (@alfcnz): youtu.be/1bBOneUMu3Y?si… * Generative modelling + iterative refinement (@sedielem): youtu.be/9BHQvQlsVdE?si… * AI for Good (@weballergy): youtu.be/tJSicw7DPVU?si… * Reasoning (@backprop2seed & I): youtu.be/CyIuM5eQZ5A?si…
We built a real-time music jamming system using RL and generative models -- you can play along with this model and learn more about our work at #ICML2024 🎶! 📄 paper: twtr.to/UFe6X 🌐 website: twtr.to/v9E5y 🕐 Tue 23 Jul 1:30 - 3 p.m. CEST 📍 Hall C 4-9 🧵
🔥 How I broke the internet today and what lessons can we learn from it? #Crowdstrike 🧐 Several things that make it a good fake that worked: 👇 1. No culprit named yet, I bring it on a platter, people like to have a culprit. 2- The culprit seems completely stupid, he is proud…
Just finding this super interesting as a Liverpool fan, who was so proud of our 2019 UCL corner kick that was "taken quickly". Now see geometric deep learning in action to study corner kicks! deepmind.google/discover/blog/…
Masked Generative Video-to-Audio Transformers with Enhanced Synchronicity Video-to-audio (V2A) generation leverages visual-only video features to render plausible sounds that match the scene. Importantly, the generated sound onsets should match the visual actions that are…
📢 Okio is closing its doors. We are ending all product offerings & open source support, but our code will remain open on GitHub. Heartfelt gratitude to all former employees, customers, users, contributors & investors for their incredible support & being part of our journey.
Training convnets on waveforms is hard—far harder than on magnitude spectrograms. "Instabilities in Convnets for Raw Audio" approaches this phenomenon from the perspective of sensitivity to initialization. IEEE Signal Processing Letters vol. 31 preprint: hal.science/hal-04528116
hi music people, i wrote a tutorial on large language models and music information retrieval. of course it's called.. LLMs <3 MIR 🥁 have fun! llms-heart-mir.github.io/tutorial
United States Trends
- 1. $CUTO 7.315 posts
- 2. WNBA 40,6 B posts
- 3. Taina 6.052 posts
- 4. #WednesdayMotivation 7.063 posts
- 5. #wednesdayfeelings 2.517 posts
- 6. Good Wednesday 33,3 B posts
- 7. Tucker 37 B posts
- 8. $ASTROS 1.903 posts
- 9. #Alphabot 6.574 posts
- 10. Dreamville 4.198 posts
- 11. Herbo 2.006 posts
- 12. #WednesdayWisdom 1.108 posts
- 13. #4YearsOfEvermore N/A
- 14. Hump Day 18,4 B posts
- 15. Mitch 77,4 B posts
- 16. Ben Rice N/A
- 17. Josh Williams N/A
- 18. $BOOST 9.508 posts
- 19. Core CPI 4.000 posts
- 20. Luis Gil 2.192 posts
Who to follow
-
Carl Thomé
@carlthome -
Stefan Lattner
@deeplearnmusic -
Javier Nistal
@latentspaces -
Pedro Sarmento
@umpedronosapato -
Emir Demirel
@_emir_demirel_ -
Christian Steinmetz
@csteinmetz1 -
Néstor Nápoles López
@napulen -
Yi-Hsuan Yang
@affige_yang -
Qiuqiang Kong
@QiuqiangK -
Magdalena Fuentes
@mfu3ntes -
Jordi Pons
@jordiponsdotme -
Elio Quinton
@elio_elioo -
Ilaria Manco
@Ilaria__Manco -
Dmitry Bogdanov
@di_bogdanov -
Nicholas J. Bryan
@NicholasJBryan
Something went wrong.
Something went wrong.