Modan Tailleur

I am a PhD student specializing in the sound field with a focus on deep learning. Through my expertise in research and my experiences as a sound engineer, I aim to contribute meaningfully to the advances of the audio research field. Here, you'll find details about my academic journey, skills, and projects. Thank you for taking the time to visit !

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

PhD Student

    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

Sept 2022 - Sept 2025 | Nantes, France
Teaching assistant

    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

Sept 2022 - Sept 2025 | Nantes, France
Sound Editor, Sound Mixer

    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

    Skills: ProTools, Reaper
Sep 2018 - July 2022 | France
Methods Engineer Intern

    Logistics Flow Management and Drone Packaging DesignLogistics Flow Management and Drone Packaging Design

    Skills: SolidWorks, SAP

Mar 2018 - Sep 2018 | Paris, France
Support to MsCs Intern

    Interned at Airbus Defense and Space, providing assistance to the team managing satellite payloads by supporting them with Excel tasks.

    Skills: VBA, Excel

April 2017 - Sep 2017 | Portsmouth, UK

Publications

Dcase 2023 Workshop

    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.

Sept 2023 | Tampere, Finland
INTERNOISE 2024

    Urban noise maps and noise visualizations traditionally provide macroscopic representations of noise levels across cities. However, those representations fail at accurately gauging the sound perception associated with these sound environments, as perception highly depends on the sound sources involved. This paper aims at analyzing the need for the representations of sound sources, by identifying the urban stakeholders for whom such representations are assumed to be of importance. Through spoken interviews with various urban stakeholders, we have gained insight into current practices, the strengths and weaknesses of existing tools and the relevance of incorporating sound sources into existing urban sound environment representations. Three distinct use of sound source representations emerged in this study: 1) noise-related complaints for industrials and specialized citizens, 2) soundscape quality assessment for citizens, and 3) guidance for urban planners. Findings also reveal diverse perspectives for the use of visualizations, which should use indicators adapted to the target audience, and enable data accessibility.

Aug 2024 | Nantes, France
EUSIPCO 2024

    This paper explores whether considering alternative domain-specific embeddings to calculate the Fréchet Audio Distance (FAD) metric can help the FAD to correlate better with perceptual ratings of environmental sounds. We used embeddings from VGGish, PANNs, MS-CLAP, L-CLAP, and MERT, which are tailored for either music or environmental sound evaluation. The FAD scores were calculated for sounds from the DCASE 2023 Task 7 dataset. Using perceptual data from the same task, we find that PANNs-WGM-LogMel produces the best correlation between FAD scores and perceptual ratings of both audio quality and perceived fit with a Spearman correlation higher than 0.5. We also find that music-specific embeddings resulted in significantly lower results. Interestingly, VGGish, the embedding used for the original Fréchet calculation, yielded a correlation below 0.1. These results underscore the critical importance of the choice of embedding for the FAD metric design.

Aug 2024 | Lyon, France
CBMI 2024

    In this paper, we introduce the Extreme Metal Vocals Dataset, which comprises a collection of recordings of extreme vocal techniques performed within the realm of heavy metal music. The dataset consists of 760 audio excerpts of 1 second to 30 seconds long, totaling about 100 min of audio material, roughly composed of 60 minutes of distorted voices and 40 minutes of clear voice recordings. These vocal recordings are from 27 different singers and are provided without accompanying musical instruments or post-processing effects. The distortion taxonomy within this dataset encompasses four distinct distortion techniques and three vocal effects, all performed in different pitch ranges. Performance of a state-of-the-art deep learning model is evaluated for two different classification tasks related to vocal techniques, demonstrating the potential of this resource for the audio processing community.

Sep 2024 | Reykjavic, Island

Projects

music streaming app
Master's Thesis

Real-time classification of extreme vocal distortion techniques used in heavy metal.

Accomplishments

    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

music streaming app
Le Monde De Pargus

A musical story written, composed, and performed by Mikael Tailleur, directed by Modan Tailleur.

Accomplishments

    Mikus, the traveling musician, embarks on an adventure to uncover what has gone awry in his universe.

    His journey will be marked by fantastic encounters: a singing forest, a pirate uncle, a mischievous mouse, an ill-tempered agave...

quiz app
Suis-moi que j'te fume

A sound fiction written and directed by Modan Tailleur and Nicolas Akl.

Accomplishments

    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.

Screenshot of web app
Invisible

Short film directed by Alexia Hanicotte, sound editing and mixing by Modan Tailleur.

Accomplishments

    "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.

Screenshot of web app
Pokeemerald French

An automatic french translation using Google Translate for the pokeemerald decompilation GitHub project.

Accomplishments

    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

École Centrale de Nantes

Nantes, France

Degree: PhD in computer science

    Relevant Courseworks:

    • Deep Learning
    • Acoustics
    • Cartography

Arts et Métiers

Châlons-en-Champagne , France

Degree: Generalist Engineer Diploma (master)

    Relevant Courseworks:

    • Mechanics
    • Database Management Systems
    • Operating Systems
    • Electronics

Politecnico Di Bari

Bari , Italy

Degree: Master in mechanical engineering

    Relevant Courseworks:

    • Mechanics applied to aeronautics
    • Management of innovation
    • Labor Law

Contact