François Grondin
Associate Professor
Sherbrooke, Quebec, Canada
Summary
👤
Senior🎓
Top SchoolFrançois Grondin is an associate professor and robotics specialist with 12+ years of experience bridging academic research and industry innovation in robot audition, sound source localization, speech enhancement, and machine learning. Trained at McGill and Université de Sherbrooke (PhD with top grades) and a former MIT CSAIL postdoc, he combines rigorous theoretical work with practical systems engineering, contributing core C and PyTorch modules to prominent open-source projects like ODAS and SpeechBrain. As co-founder and CSO of DARIT Technologies, he translates research prototypes into products while continuing to lead university labs and teach advanced signal-processing topics. His work is notable for implementing real-time, multi-microphone beamforming and source-separation components that power both research toolkits and embedded audition systems.
12 years of coding experience
7 years of employment as a software developer
Doctor of Philosophy (Ph.D.), Robotics, 4.30/4.30, Doctor of Philosophy (Ph.D.), Robotics, 4.30/4.30 at Université de SherbrookeBachelor of Electrical Engineering, 3.96/4.00, Bachelor of Electrical Engineering, 3.96/4.00 at McGill University
English, French
Github Skills (19)
matrix-decomposition10
pytorch10
multithreading10
beam10
audio-processing10
c1110
c1710
speech-recognition10
eigenvalue10
realtime9
speech-to-text9
asr9
localization9
deep-learning9
audio9
Programming languages (3)
Github contributions (5)
introlab/odas
Jul 2017 - Jul 2022
ODAS: Open embeddeD Audition System
Role in this project:
Back-end Developer
Back-end DeveloperContributions:1 review, 219 commits, 22 PRs in 5 years 1 month
Contributions summary:François added several source files, likely related to the Open embeddeD Audition System (ODAS) project. These files seem to implement various components such as connectors, messages, and modules related to audio processing, including spectrum analysis, track management, and source separation. The code changes demonstrate the user's familiarity with C programming and the development of concurrent, multi-threaded applications. The user's additions contribute to the overall functionality of the ODAS system, which involves beamforming, localization, and real-time audio processing.
odasbeamformerroboticstrackingembedded
speechbrain/speechbrain
Jul 2020 - Nov 2021
A PyTorch-based Speech Toolkit
Role in this project:ML Engineer
ML EngineerContributions:8 commits, 1 PR, 3 comments in 1 year 3 months
Contributions summary:François primarily contributed to the `speechbrain/speechbrain` repository by implementing and modifying modules related to multi-microphone signal processing and eigenvalue decomposition. Their work involved the creation of classes for beamforming techniques such as Delay and Sum, MVDR, GEV, and GCC-PHAT, as well as a Covariance module. These changes are critical for enabling advanced audio processing functionalities within the PyTorch-based speech toolkit. Further contributions included fixing and refining existing modules, enhancing the capabilities of the repository's multi-microphone processing features.
voice-recognitionasrspeech-recognitionspeech-separationspeaker-verification
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.