Stefan Lattner
stefanlattner.bsky.social
Stefan Lattner
@stefanlattner.bsky.social
Research Leader @ Sony CSL Paris
Zero-shot Musical Stem Retrieval with Joint-Embedding Predictive Architectures
A. Riou, S. Lattner, A. Gagneré, G. Hadjeres, S. Lattner, G. Peeters
Tuesday, April 8 ( pm): Music analysis I
April 8, 2025 at 6:40 AM
Hybrid Losses for Hierarchical Embedding Learning
H. Tian, S. Lattner, B. McFee, C. Saitis
Tuesday, April 8 ( pm): Music analysis I
April 8, 2025 at 6:40 AM
Accompaniment Prompt Adherence: A Measure for Evaluating Music Accompaniment Systems
M. Grachten, J. Nistal
Friday, April 11 ( am): Applied Signal Processing Systems

Estimating Musical Surprisal in Audio
M. Bjare, G. Cantisani, S. Lattner and G. Widmer
Wednesday, April 9 ( am): Music analysis II
April 8, 2025 at 6:40 AM
We also show that our IC estimates can help predict EEG measurements. 💆‍♀️

Surprisal can be used for segment boundary detection and to simulate the information processing of a listener. 🎶 🧠

📜 Link to the paper: arxiv.org/pdf/2501.07474

Model weights are soon to come! 🏋️

💫✨ #SonyCSLMusic 💫✨
arxiv.org
January 21, 2025 at 3:26 PM
3/ Results show:

- Higher fidelity (FAD ↓ by 20%)
- Better adherence to text & audio prompts (APA ↑)
- Faster generation with 5-step inference!

AI-assisted music production. 🎼💡 Let us know your thoughts!

Congrats to the authors Javier Nistal and Marco Pasini!

#AI #MusicGeneration #Transformers
January 20, 2025 at 1:44 PM
2/ 🎤 What’s new?

- Stereo output with superior fidelity
- Bridging the gap in Text-to-audio CLAP embeddings 📝🎵
- Faster inference using a consistency framework ⚡

Audio examples: sonycslparis.github.io/improved_dar/ 🎶👂
Improving Musical Accompaniment Co-creation via Diffusion Transformers
sonycslparis.github.io
January 20, 2025 at 1:43 PM
1/ Building on Diff-A-Riff, we’ve upgraded to a stereo-capable autoencoder & replaced the U-Net with a Diffusion Transformer (DiT) to improve quality, diversity, and control. 🎧📈 Plus, our model generates high-quality audio with fewer denoising steps. 🚀
January 20, 2025 at 1:42 PM
Hybrid Losses for Hierarchical Embedding Learning
H. Tian, S. Lattner, B. McFee, C. Saitis

Congrats to the authors!
January 14, 2025 at 12:55 PM
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
January 14, 2025 at 12:54 PM