michael turbot

Managing the Music Technology Promotion Office of Sony Computer Science Laboratories

Previous : Head of innovation @ Sony Music Entertainment France

[Jonas Čeika @Jonas_Ceika]

I sent ChatGPT an audio file of a series of FART sound effects and asked what it thinks of "my music" and this is what it said

[Alain Riou @howariou]

Eminem sampled Aerosmith, 50 Cent sampled Nina Simone, everybody sampled Chic... Many great songs sampled existing ones!

Detecting this is the topic of our latest paper with @serrjoa at @SonyAI Barcelona 😎

tl;dr: multi-track dataset + few tricks = +18% boost over SOTA 🚀

1/N

[Sony CSL (Paris) @SonyCSLParis]

📽️ Join us for our #seminar with #MarcoPasini, PhD student at #QueenMaryUniversity of London

In collaboration with @SonyCSLMusic he researches ways to make generative models for audio and music both faster and more controllable

⚡Don’t miss it: https://t.co/ymGOpMzFPL

[Stefan Lattner @deeplearnmusic]

😃Accepted @ieeeICASSP papers of @SonyCSLMusic:

Accompaniment Prompt Adherence: A Measure for Evaluating Music Accompaniment Systems
M. Grachten, J. Nistal

Estimating Musical Surprisal in Audio
M. Bjare, G. Cantisani, S. Lattner and G. Widmer

Hybrid Losses for Hierarchical Embedding Learning
H. Tian, S. Lattner, B. McFee, C. Saitis

Music2Latent2: Audio Compression with Summary Embeddings and Autoregressive Decoding
M. Pasini, S. Lattner, G. Fazekas

Zero-shot Musical Stem Retrieval with Joint-Embedding Predictive Architectures
A. Riou, S. Lattner, A. Gagneré, G. Hadjeres, S. Lattner, G. Peeters

Congrats to the authors!
@latentspaces @howariou @GiorgiaCanti @tiianhk @marco_ppasini @GeoffroyPeeters @gaetan_hadjeres @SonyCSLParis

[michael turbot @mturbot]

Hey @Garmin , for 2025 could we be able to see when - on the load page - be able to see what activity changed the « load »just by clicking on the dot or the line ?

[SonyCSL(Paris)_Music Team @SonyCSLMusic]

💡If you missed it, we released our new AI-tool, #DrumGAN, which allows you to generate flexible drum sounds with ease

Here is a full blogpost for a detailed look at it
+ free download the 1st #AI-drum kits made by #Twenty9 during our collaboration

➡️🎁 https://t.co/xx5CDlxV1c

[Stefan Lattner @deeplearnmusic]

🥳 New publication announcement!

Marco Pasini solved the problem of error accumulation in continuous autoregressive models (CAMs), making it possible to generate sequences without the need for prior tokenization. Say goodbye to RVQ codecs (use music2latent 😉).

@SonyCSLMusic

[Sony CSL (Paris) @SonyCSLParis]

📡We'll be in #Cannes all day on November 29 to talk about market gardening. Come and join us for #Symposium

🪴What models for small-scale market gardening?

🌐The conference will also be broadcast online on our networks ➡️ free registration required: https://t.co/zdMp7rnUqm

[michael turbot @mturbot]

Super moment à Kigali ! Bravo !

[Mamby Laye Diomandé @LayeDiom]

🌍 Lors de #Acces2024, j’ai eu l’opportunité de participer à un panel dédié aux innovations et opportunités dans l’industrie musicale africaine et mondiale aux côtés de Thomas Zandrowicz, Esther NAAH, @mturbot et Kobby Ankomah Graham.

[Yuki Mitsufuji @mittu1204]

A list of diffusion works & tutorial (at #ISMIR2024) from our lab!

[ML]
https://t.co/aZcO6PLQXM #NeurIPS24 (GenWarp: Novel View Synthesis)
https://t.co/MNyOOmh14g #NeurIPS24 (PaGoDA: Multi-Scale 1 Step Generator)
https://t.co/izwquz3MLR #ICLR24 (CTM: Fast Image Gen.)
https://t.co/luObWNJC3P #ICLR24 (MPGD: Guided Diffusion)
https://t.co/RquawBXlMJ #ICML23 (FP-Diff: Consistency-type Model)
https://t.co/x3dWQOnQbU #ICML23 (Blind Inverse)

[Audio/NLP]
https://t.co/OfO7QjVe4h #ACL24 (Knowledge Gen.)
https://t.co/aT7YR2Zguy #IJCAI24 (Music Editing)
https://t.co/nMnshxUVNr #ICASSP24 (Declipping)
https://t.co/rii9fwD1jr #ICASSP24 (Speech Enh.)
https://t.co/WTmL50Z4Ea #ICASSP23 (Music Transcription)
https://t.co/w8Aryk5TtT #ICASSP23 (Vocoder)
https://t.co/GYO4JkSG63 #ICASSP23 (Dereverb)
https://t.co/xg7OIdVfZo #INTERSPEECH23 (Speech Enh.)

[arXiv Sound @ArxivSound]

``Music Foundation Model as Generic Booster for Music Downstream Tasks,'' WeiHsiang Liao, Yuhta Takida, Yukara Ikemiya, Zhi Zhong, Chieh-Hsin Lai, Giorgio Fabbro, Kazuki Shimada, Keisuke Toyama, Kinwai Cheuk, Marco Martinez, Shusuke Takahashi, Stefan Uhl… https://t.co/yrGBaBkTgQ

[Audio and Speech Processing Papers @AudioAndSpeech]

Music Foundation Model as Generic Booster for Music Downstream Tasks. https://t.co/Tq1rT6he5a

[Sony CSL (Paris) @SonyCSLParis]

Our #MusicTeam just released its 1st AI-prototype: #SampleMatch !

Try it now on @TechHubbySony: https://t.co/JiC0k0bSEo

Congrats Team 👏

#techhubsony #sonycslparis #aimusic #airesearch #musicprototype

[Sony CSL (Paris) @SonyCSLParis]

🌱Midori Farm: where tradition meets technology in urban agriculture

🌿We’re combining the time-honored #FrenchMethod market gardening with modern tools to bring sustainable farming to urban spaces

Our goal is to explore the future of small-scale microfarms in peri-urban areas

[Stefan Lattner @deeplearnmusic]

😯Surprisal in music is an often underestimated concept. It's not only valuable for music analysis but can also be leveraged to control complexity and structure in music generation.

Check out our @ISMIRConf paper, where we use Information Content curves as a control signal for polyphonic music generation:

📜https://t.co/e5xrNQXB2y

Great work by @BjareMathias !🤓 @SonyCSLMusic @cpjku @SonyCSLParis

[SonyCSL(Paris)_Music Team @SonyCSLMusic]

🎶New paper alert!

📜#MaartenGrachten & @latentspaces introduce Accompaniment Prompt Adherence (APA)—a new metric for evaluating AI-generated musical accompaniments.

➡️https://t.co/G2SH7yCtw1
⚙️https://t.co/RS9mLEDMFE…

#SonyCSLParis #AI #MusicTech #CLAP

[SonyCSL(Paris)_Music Team @SonyCSLMusic]

🎼 To keep your Summer entertained, we're releasing a new Reggae demo produced by #CarliNistal using our AI model #DiffARiff

We're working on more demos in multiple musical styles for you to listen to before heading back to work!

#aimusic #ai #research #innovation #sonycsl

[Stefan Lattner @deeplearnmusic]

🥳Another ISMIR Paper released (+model weights)!!

Music2Latent: Consistency Autoencoders for Latent Audio Compression
Marco Pasini, Stefan Lattner, George Fazekas

64x compression, 48kHz, HQ reconstruction

- End-to-end training with only one loss term
- Representations competitive in downstream tasks
- First Consistency Autoencoder (in any domain)

📜 Paper: https://t.co/pIreObzAlY
🌍 Code + Weights: https://t.co/gzqIsV9phm

@ISMIRConf @SonyCSLMusic

More below 👇

[Stefan Lattner @deeplearnmusic]

🥳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: https://t.co/NjUiUMRIPC
🌍 Code: https://t.co/QjL3jDPMXu

For more info, check out the tweet below 👇