User Pic

Théo Mariotte

Junior lecturer


LST ( Le Mans )

(+33) 02 43 83 38 58

Theo.Mariotte[at]univ-lemans.fr

https://lium.univ-lemans.fr/en/team/theo-mariotte-2/


Research Activities:

Project(s): ESPERANTO

 

Biography

Initially trained as an acoustics and vibration engineer, I turned to research via a collaborative thesis between the computer science and acoustics laboratories at the University of Le Mans (LIUM & LAUM). I then started a post-doctorate at Télécom Paris, in the Image Data Signal team, before being recruited as a lecturer at LIUM.

My research focuses on audio signal processing tasks, in particular speech, such as speaker segmentation and grouping, and source separation. I’m particularly interested in the development of explainable and interpretable AI models to better understand the objects we manipulate.

Publications

HAL Publications  Hal https://hal.archives-ouvertes.fr/search/index/?qa[authIdHal_s][]=theo-mariotte

LIUM Publications - 11

[1]Théo Mariotte, Anthony Larcher, Silvio Montrésor, Jean-Hugh Thomas. ASoBO: Attentive Beamformer Selection for Distant Speaker Diarization in Meetings. Interspeech, International Speech Communication Association (ISCA), Sep 2024, Kos / Greece, Greece. <hal-04602289>
[2]Martin Lebourdais, Théo Mariotte, Antonio Almudévar, Marie Tahon, Alfonso Ortega. Explainable by-design Audio Segmentation through Non-Negative Matrix Factorization and Probing. Interspeech 2024, International Speech Communication Association (ISCA), Sep 2024, Kos / Greece, France. <hal-04617131>
[3]Martin Lebourdais, Pablo Gimeno, Théo Mariotte, Marie Tahon, Alfonso Ortega, et al.. 3MAS: a multitask, multilabel, multidataset semi-supervised audio segmentation model. Speaker and Language Recognition Workshop - Odyssey, Jun 2024, Québec (CA), Canada. <hal-04591532>
[4]Antonio Almudévar, Théo Mariotte, Alfonso Ortega, Marie Tahon. Unsupervised multiple domain translation through controlled Disentanglement in variational autoencoder. ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Apr 2024, Seoul, France. pp.7010-7014, ⟨10.1109/ICASSP48485.2024.10446649⟩. <hal-04638710>
[5]Théo Mariotte, Antonio Almudévar, Marie Tahon, Alfonso Ortega. AN EXPLAINABLE PROXY MODEL FOR MULTILABEL AUDIO SEGMENTATION. International Conference on Acoustics Speech and Signal Processing, IEEE, Apr 2024, Seoul (Korea), France. <hal-04393946>
[6]Théo Mariotte, Anthony Larcher, Silvio Montrésor, Jean-Hugh Thomas. Channel-Combination Algorithms for Robust Distant Voice Activity and Overlapped Speech Detection. IEEE/ACM Transactions on Audio, Speech and Language Processing, In press. <hal-04454362>
[7]Théo Mariotte, Anthony Larcher, Silvio Montrésor, Jean-Hugh Thomas. Multi-microphone Automatic Speech Segmentation in Meetings Based on Circular Harmonics Features. Interspeech 2023, international Speech Communication Association (ISCA), Aug 2023, Dublin, Ireland. <hal-04117442>
[8]Martin Lebourdais, Théo Mariotte, Marie Tahon, Anthony Larcher, Antoine Laurent, et al.. Joint speech and overlap detection: a benchmark over multiple audio setup and speech domains. Le Mans Université. 2023. <hal-04133268>
[9]Théo Mariotte, Anthony Larcher, Silvio Montrésor, Jean-Hugh Thomas. Microphone Array Channel Combination Algorithms for Overlapped Speech Detection. Interspeech 2022 Human and Humanizing Speech Technology, Sep 2022, Incheon, South Korea. <hal-03713385>
[10]Théo Mariotte, Anthony Larcher, Jean-Hugh Thomas, Silvio Montrésor. Détection de parole superposée distante à l’aide d’une antenne de microphones. 34e Journées d'Étude sur la Parole, Jun 2022, Île de Noirmoutier, France. <hal-03700008>
[11]Théo Mariotte, Anthony Larcher, Jean-Hugh Thomas, Silvio Montrésor. Traitement multi-microphone pour la segmentation automatique de la parole en réunion. 16ème Congrès Français d'Acoustique, Apr 2022, Marseille, France. <hal-03700014>