Aurian Quélennec
@aurian-sound.bsky.social
🎓 PHD student @ Télécom Paris - ADASP Team
👨💻 Building SSL foundation models for audio and music
👨💻 Building SSL foundation models for audio and music
Pinned
I released MATPAC++, an audio SSL foundation model with SOTA performances. 🥇
It solves uncertainty in Masked Audio Modelling by selecting the best prediction among several hypotheses. 🧠
📝 Paper: arxiv.org/pdf/2508.12709
👨💻 Code & weights soon: github.com/aurianworld/...
It solves uncertainty in Masked Audio Modelling by selecting the best prediction among several hypotheses. 🧠
📝 Paper: arxiv.org/pdf/2508.12709
👨💻 Code & weights soon: github.com/aurianworld/...
Reposted by Aurian Quélennec
A review of 25 years of Music Information Retrieval (MIR) research covers achievements, practices, evaluations, and future challenges; emphasizes signal processing, open research, industry engagement, and diversity.
Twenty-Five Years of MIR Research: Achievements, Practices, Evaluations, and Future Challenges
Geoffroy Peeters, Zafar Rafii, Magdalena Fuentes, Zhiyao Duan, Emmanouil Benetos, Juhan Nam, Yuki Mitsufuji
arxiv.org
November 11, 2025 at 11:03 AM
A review of 25 years of Music Information Retrieval (MIR) research covers achievements, practices, evaluations, and future challenges; emphasizes signal processing, open research, industry engagement, and diversity.
I released MATPAC++, an audio SSL foundation model with SOTA performances. 🥇
It solves uncertainty in Masked Audio Modelling by selecting the best prediction among several hypotheses. 🧠
📝 Paper: arxiv.org/pdf/2508.12709
👨💻 Code & weights soon: github.com/aurianworld/...
It solves uncertainty in Masked Audio Modelling by selecting the best prediction among several hypotheses. 🧠
📝 Paper: arxiv.org/pdf/2508.12709
👨💻 Code & weights soon: github.com/aurianworld/...
August 19, 2025 at 12:41 PM
I released MATPAC++, an audio SSL foundation model with SOTA performances. 🥇
It solves uncertainty in Masked Audio Modelling by selecting the best prediction among several hypotheses. 🧠
📝 Paper: arxiv.org/pdf/2508.12709
👨💻 Code & weights soon: github.com/aurianworld/...
It solves uncertainty in Masked Audio Modelling by selecting the best prediction among several hypotheses. 🧠
📝 Paper: arxiv.org/pdf/2508.12709
👨💻 Code & weights soon: github.com/aurianworld/...
I am excited to share the code from our paper MATPAC, which I will present at ICASSP next week.🇮🇳
This code includes:
⚡Inference code, which you can pip install.
⚙️Full training code for reproducibility.
👨🏾💻 github.com/aurianworld/...
This code includes:
⚡Inference code, which you can pip install.
⚙️Full training code for reproducibility.
👨🏾💻 github.com/aurianworld/...
GitHub - aurianworld/matpac: Official MATPAC implementation and trained model's weights.
Official MATPAC implementation and trained model's weights. - aurianworld/matpac
github.com
March 31, 2025 at 1:49 PM
I am excited to share the code from our paper MATPAC, which I will present at ICASSP next week.🇮🇳
This code includes:
⚡Inference code, which you can pip install.
⚙️Full training code for reproducibility.
👨🏾💻 github.com/aurianworld/...
This code includes:
⚡Inference code, which you can pip install.
⚙️Full training code for reproducibility.
👨🏾💻 github.com/aurianworld/...