Key improvements: ✔ Summary embeddings capture global features efficiently 🏆 ✔ Autoregressive consistency decoding ensures seamless audio reconstruction 🎼 ✔ Better reconstruction & downstream task performance 📊 This sets a new benchmark for neural audio compression. 🚀 #AI #AudioCompression @SonyCSLMusic

🤩From our series "@ieeeICASSP paper released", we announce that "Zero-shot Musical Stem Retrieval with Joint-Embedding Predictive Architectures" is online! 📜 Paper: Thx to my colleagues @howariou @GeoffroyPeeters @gaetan_hadjeres! 🎶@SonyCSLMusic 🎶

Our @ieeeICASSP paper "Hybrid Losses for Hierarchical Embedding Learning" by @tiianhk et al. is now online! 💫 We assess the organization of a hierarchical embedding space using different (combinations of) losses. We improve on the SOTA using (novel) per-level and binary losses. 📜 Paper: @c4dm @SonyCSLMusic @SonyCSLParis

Recently, I had the honour of giving a keynote speech on Audio Representation Learning and Generation at the DMRN+ workshop at @c4dm at Queen Mary University. 🎬🎙️ Recording: 🎶 More Info: @SonyCSLMusic

📜Link to the paper: The code and model weights will be online soon! @SonyCSLMusic @SonyCSLParis

3/ Results show: - Higher fidelity (FAD ↓ by 20%) - Better adherence to text & audio prompts (APA ↑) - Faster generation with 5-step inference! AI + human co-creation in music. 🎼💡 Let us know your thoughts! Congrats to the authors @latentspaces and @marco_ppasini! @SonyCSLMusic #AI #MusicGeneration #Transformers

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: 🎶👂

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! 🚀

@HoltSkinner12 @ISMIRConf @Gabolsgabs Thank you Holt! Feedback on the book is always welcome btw..

😃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

RT @tuktoe: Delighted to announce that our EEG2Music paper has been accepted for ICASSP 2025! 🎉 This work represents an important step forw…

Thanks for the warm welcome in London today at the DMRN workshop of @c4dm full of insightful talks and passionate people. Music research is in good hands! ♥️😊