12-12-2024: NeurIPS 2024
NeurIPS 2024 : 6 papers accepted! ≥≥
The S²A team is affiliated with Telecom Paris’ in-house research laboratory, LTCI. Team’s expertise spans several disciplines: probabilistic modeling, statistics, optimization, (audio) signal processing, machine/deep-learning and computational linguistics. The team mobilizes them to produce methodologically sound research in response to some of the challenges posed by the nature and format of modern data, as well as the high societal expectations surrounding the development of AI solutions that are not only effective but also reliable, robust, ethical, frugal and integrate sustainability issues. The team's research activities revolve around four main themes, which are often intertwined in AI applications:
A significant fraction of our research is performed within national and international collaborative projects, with numerous academic and industrial partners.
NeurIPS 2024 : 6 papers accepted! ≥≥
5 papers accepted for the ADASP group ! INTERSPEECH ≥≥
Our group is hiring a master 2 intern on the topic of computational socio-linguistics! Important informations Duration: 5-6 months, starting from March 1... ≥≥
MapAIE - Mapping AI Ethics: Mapping Artificial Intelligence Ethics Charters and Manifestos. The MapAIE corpus is a collection of 436 common charters and mani... ≥≥
We are looking for an intern on the topic of particle swarm algorithms for nonconvex optimization see attached pdf. ≥≥
The Dialogues in Games corpus (DinG) is composed of transcriptions of 10 recordings of people playing the boardgame Catan, in French. We share the transcribe... ≥≥
The github repository for the structured prediction library developped with HiParis! can be found here. ≥≥
Title: Advancing Medium-/Low-resource Language Generation with LLMs: Benchmarking, Personalization, and Model Optimization Abstract Recent advancements in G... ≥≥
Alessandro Ragano will give a talk on Perceptual Metric Learning for Speech Quality Assessment ≥≥
Abstract Machine listening systems often rely on fixed taxonomies to organize and label audio data, key for training and evaluating deep neural networks (DNN... ≥≥