About
- Languages: French (native), English (fluent), Italian (basic), German (basic), Japanese (basic)
- Programming Languages: Python, C, C++, HTML/CSS, Java, JavaScript, Bash, VBA
- Databases: MySQL, PostgreSQL
- Libraries: PyTorch, TensorFlow, NumPy, Pandas
Experience
Sound source detection for the sensitive mapping of urban sound environments.
👉 Deep Learning: classification, generative models
👉 Statistical analysis, experimental design, auditory perception, cognitive psychology
👉 Acoustic scene analysis, audio signal processing, programming (Python)
Skills: Computer Science, Statistics, Python, Deep Learning, Acoustics, Cartography
Teaching students from the 1st to the 3rd cycle
👉 Deep Learning
👉 algorithms and programming
👉 signal processing
👉 SQL database
Skills: Pedagogy, Python, C++, SQL, Deep Learning, Acoustics
Freelance sound engineer working for radio, music and cinema
👉 Sound mixing and sound editing for the cinema industry, for music, and for sound fictions
👉 Direction of a radio program for Prun' radio
Logistics Flow Management and Drone Packaging DesignLogistics Flow Management and Drone Packaging Design
Skills: SolidWorks, SAP
Interned at Airbus Defense and Space, providing assistance to the team managing satellite payloads by supporting them with Excel tasks.
Skills: VBA, Excel
Publications
Slow or fast third-octave bands representations (with a frame resp. every 1-s and 125-ms) have been a de facto standard for urban acoustics, used for example in long-term monitoring applications. It has the advantages of requiring few storage capabilities and of preserving privacy. As most audio classification algorithms take Mel spectral representations with very fast time weighting (ex. 10- ms) as input, very few studies have tackled classification tasks using other kinds of spectral representations of audio such as slow or fast third-octave spectra.
In this paper, we present a convolutional neural network ar- chitecture for transcoding fast third-octave spectrograms into Mel spectrograms, so that it could be used as input for robust pre-trained models such as YAMNet or PANN models. Compared to training a model that would take fast third-octave spectrograms as input, this approach is more effective and requires less training effort. Even if a fast third-octave spectrogram is less precise both on time and frequency dimensions, experiments show that the proposed method still allows for classification accuracy of 62.4% on UrbanSound8k and 0.44 macro AUPRC on SONYC-UST.
Projects
Real-time classification of extreme vocal distortion techniques used in heavy metal.
The study proposes the development of a real-time plugin utilizing machine learning for the classification of extreme vocal techniques used in heavy metal music.
The approach includes the creation of custom models and the introduction of innovative acoustic descriptors, DAFCC, inspired by MFCC, enhancing both accuracy and computational efficiency
A musical story written, composed, and performed by Mikael Tailleur, directed by Modan Tailleur.
A sound fiction written and directed by Modan Tailleur and Nicolas Akl.
Despite Fabien's hostile attitude during his job interview, Corentin was eventually accepted for an internship at Cintroflex.
While not the professional experience of his dreams, this internship still allows him to spend some more time with his grandmother. Unfortunately for him, Fabien still has a few surprises in store.
Short film directed by Alexia Hanicotte, sound editing and mixing by Modan Tailleur.
"Invisible" is the story of Lola, a 17-year-old high school student. Lola loves to party with her friends, play drinking games, and dance with them until the end of the night. But tonight, Lola doesn't feel well; she no longer wants to play, no longer wants to drink.
Winner of the Schools Award at the 2021 Nikon Festival.
An automatic french translation using Google Translate for the pokeemerald decompilation GitHub project.
Pokeemerald is a decompilation project for Pokémon Emerald, aiming to unravel and understand the game's source code. This approach enables developers to make nuanced modifications to the mechanics of the game for a customized experience. Unfortunately, Pokeemerald is only able to compile the game in English. This project aims at making a french Pokeemerald, partly using google translate.
Education
Nantes, France
Degree: PhD in computer science
- Deep Learning
- Acoustics
- Cartography
Relevant Courseworks:
Châlons-en-Champagne , France
Degree: Generalist Engineer Diploma (master)
- Mechanics
- Database Management Systems
- Operating Systems
- Electronics
Relevant Courseworks:
Bari , Italy
Degree: Master in mechanical engineering
- Mechanics applied to aeronautics
- Management of innovation
- Labor Law
Relevant Courseworks: