- ๐ฌ I hold a PhD in Computer Science, with a primary research focus on artificial intelligence applied to audio analysis and natural language processing. My doctoral dissertation concentrated on Automated Audio Captioning, a multimodal task aimed at developing systems capable of generating natural language sentences to describe audio files.
- ๐ญ I am currently working on the TIRIS-SILENCE project, which aims to study and extract information from audio files recorded in extreme environments such as Mars.
- ๐ฑ I am also looking to learn new deep learning tasks, such as spoken language understanding and automatic speech recognition.
- ๐ Pronouns: he/him
- ๐ซ How to reach me: labbeti.pub@gmail.com
PhD in computer science, focused on automated audio captioning. Always looking to learn new things about deep learning. I also like hot chocolate and my cats.
-
IRIT
- Toulouse, France
-
22:41
(UTC +01:00) - labbeti.github.io
- https://orcid.org/0000-0002-7219-5463
Pinned Loading
-
-
aac-metrics
aac-metrics PublicMetrics for evaluating Automated Audio Captioning systems, designed for PyTorch.
-
dcase2024-task6-baseline
dcase2024-task6-baseline PublicDCASE2024 Challenge Task 6 baseline system (Automated Audio Captioning)
Python 5
-
torchoutil
torchoutil PublicCollection of functions and modules to help development in PyTorch.
Python 2
-
conette-audio-captioning
conette-audio-captioning PublicCoNeTTE: An efficient Audio Captioning system leveraging multiple datasets with Task Embedding
Python 14
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.