Étienne Labbé
/etjɛn labe/
I’m a PhD student currently working on Artificial Intelligence for computational analysis of audio events using deep learning methods. My research focuses on Automated Audio Captioning, a multimodal task aiming to build systems capable of describing an audio file using a sentence written in natural language. I am currently working at the Computer Science Research Institute of Toulouse, in France.
During my PhD, I have worked a lot with recent deep learning approaches, treated crossmodal data and worked on several supercomputers like Jean Zay. In a few months, I’m going to finish my PhD thesis, but I’d like to continue participating in the development of AI to help improve society.
News
Dec 6, 2023 | We created a simple interface to test our recent model CoNeTTE, available here! |
---|---|
Nov 9, 2023 | We published the source code to test the CoNeTTE audio captioning system, available on Github and as a Pip package! |
Sep 6, 2023 | We submitted a paper to the ICASSP2024 conference, entitled “Multilingual Audio Captioning using machine translated data”! |
Aug 10, 2023 | We wrote a new paper entitled “CoNeTTE: An efficient Audio Captioning system leveraging multiple datasets with Task Embedding”, available on arxiv! |
Aug 1, 2023 | Our paper “Killing two birds with one stone: can an audio captioning system also be used for audio-text retrieval?” has been accepted for the DCASE2023 Workshop! |