Audio Data Analysis and Signal Processing @ Télécom Paris

Welcome

The ADASP group (Audio Data Analysis and Signal Processing) is a research group associated to the S²A team, and affiliated with Telecom Paris’ in-house research laboratory: the LTCI.

A significant fraction of our research is performed within national and international collaborative projects, with numerous academic and industrial partners.

 

Research topics

Prefer a formal description?

 

 

The ADASP group develops data analysis and artificial intelligence (AI) methods primarily targeting audio data. These developments rely on signal processing and machine learning techniques, focusing on:

• data decomposition and representation learning methods, especially self-supervised learning,
• as well as parametric and generative modelling methods.

Such methods are employed essentially to address two types of tasks:

• source separation,
• human activity-related scene and content analysis, notably using classification methods;

with applications in:

• machine listening,
• music information retrieval,
• speech processing,
• audio signal transformation (denoising, enhancement, dereverberation, spatialisation),
• heterogeneous, multiview or multimodal data analysis, especially multimedia content analysis,
• physiological signal analysis, especially M/EEG data, dereverberation, spatialisation.

---

Recent Posts