📄18 présidentes et présidents d'université ont déjà signé le communiqué commun contre les mesures contenus dans le projet de loi immigration.

On veut du chauffage dans les écoles plutôt que des #JO ! un mois et demi à 15 °C pour les petits de #EcoleLevertParis20 ! Enfants et prof malades. Merci de réagir #mairieparis #educationnationale

10 papers from the Audio group ADASP of Télécom-Paris will be presented at ICASSP 2014 IEEE ICASSP. --- Paper #1: Bernardo Torres et al. "Unsupervised Harmonic Parameter Estimation Using Differentiable DSP and Spectral Optimal Transport"

10 papers from the Audio group ADASP of Télécom-Paris will be presented at IEEE ICASSP 2024 --- Paper #3: Antonin Gagneré et al. "Adapting Pitch-Based Self Supervised Learning Models For Tempo Estimation". This paper provides a new SOA for SSL-based tempo estimation.

ISMIR Conference 2024 CfP is out! Abstracts due on April 5th and Full Papers due on April 12th. Also, did you see our fancy new logo? See you in San Francisco in November, titans! 😍

10 papers from the Audio group ADASP of Télécom-Paris will be presented at IEEE ICASSP 2024 --- Paper #4: Teysir Baoueb et al. "SpecDiff-GAN: A Spectrally-Shaped Noise Diffusion GAN for Speech and Music Synthesis"

10 papers from the Audio group ADASP of Télécom-Paris will be presented at IEEE ICASSP 2024 --- Paper #5: Elio Gruttadauria et al. "Online Speaker Diarization Of Meetings Guided By Speech Separation" hal.science/S2A/hal-044190…

10 papers from the Audio group ADASP of Télécom-Paris will be presented at IEEE ICASSP 2024 --- Paper #6: Aurian Quelennec et al. "On The Choice Of The Optimal Temporal Support For Audio Classification With Pre-Trained Embeddings" hal.science/hal-04360221

10 papers from the Audio group ADASP of Télécom-Paris will be presented at IEEE ICASSP 2024 --- Paper #7: Côme Peladeau and Geoffroy Peeters "Blind estimation of audio effects using an auto-encoder approach and differentiable signal processing" arxiv.org/pdf/2310.11781…

10 papers from the Audio group ADASP of Télécom-Paris will be presented at IEEE ICASSP 2024 --- Paper #8: Haocheng Liu et al. "GLA-Grad: A Griffin-Lim Extended Waveform Generation Diffusion Model" hal.science/hal-04424100

10 papers from the Audio group ADASP of Télécom-Paris will be presented at IEEE ICASSP 2024 --- Paper #9: Gaël Richard et al. "A Fully Differentiable Model for Unsupervised Singing Voice Separation" arxiv.org/abs/2401.16837

10 papers from the Audio group ADASP of Télécom-Paris will be presented at IEEE ICASSP 2024 (SSL workshop) Paper #10: Alain Riou et al. "Investigating Design Choices in JEPA for General Audio Representation Learning" Alain Riou Gaëtan Hadjeres Stefan Lattner SonyCSL(Paris)_Music Team

📢Abstract Submission Deadline this Friday, Apr 5, 2024📢 Visit ismir2024.ismir.net/authors/call-f… for more details on the submission process. #ismir2024 #CallForPapers #music

Best Student Paper award: “Adapting Frechet Audio Distance for Generative Music Evaluation” by Azalea Gui, Hannes Gamper, Sebastian Braun, and Dimitra Emmanouilidou. ieeexplore.ieee.org/document/10446…

Another great experience with Air France flight canceled without telling me and booking tickets for yesterday 🙃😡

Signals with a high degree of autocorrelation (such as pitched signals) make the training of convnets on raw audio unstable. For Gaussian initialization, the greater the input’s autocorrelation, the greater the variance of the output. Huge relief seeing these kinds of papers <3

🥳Happy to share: The SonyCSL(Paris)_Music Team team got 5 papers accepted for ISMIR Conference 2024! Diff-A-Riff: Musical Accompaniment Co-creation via Latent Diffusion Models J. Nistal, M. Pasini, C. Aouameur, M. Grachten, S. Lattner Controlling Surprisal in Music Generation via Information

``Masked Latent Prediction and Classification for Self-Supervised Audio Representation Learning,'' Aurian Quelennec, Pierre Chouteau, Geoffroy Peeters, Slim Essid, ift.tt/hzyjDQd