
Paul-Gauthier Noé
Présentation
I am a researcher in Computer Science (chargé de recherche CNRS) in Marseille. In 2025, I joined the team QARMA in the Laboratoire d'Informatique et des Systèmes.
My main research interests are Calibration of probabilities, Information theory, Machine learning and Privacy in Speech technologies.
In 2024, I worked as a postdoctoral researcher at Statify, a joint team of Inria and Laboratoire Jean Kuntzmann in Grenoble.
In 2023, I received a PhD in Computer Science in Avignon Université under the supervision of Jean-François Bonastre and Driss Matrouf. I was working for the international JST-ANR VoicePersonae project. My thesis is named Representing evidence for attribute privacy: bayesian updating, compositional evidence, and calibration and can be found here.
Education:
- 2019-2023, Avignon Université: PhD in Computer Science.
- 2018-2020, KTH Royal Institute of Technology, Stockholm: M.Sc.Eng. in Computer Science and Electrical Engineering.
- 2015-2019, Grenoble Institute of Technology: M.Sc.Eng. in Signal and Image Processing, Communication Systems, Multimedia (Phelma Sicom). B.Eng. Phelma.
Research visits:
- October 2023, University of Bristol, in the team of Prof. Peter Flach,
- June 2022-September 2022, National Institute of Informatics, Tokyo, in the team of Prof. Junichi Yamagishi.
Awards:
- Best thesis award 2023 from the Association Francophone de la Communication Parlée (AFCP), a special interest group of the International Speech Communication Association (ISCA).
- Best poster contribution at CodaWork2024 for our work on Compositional Discriminant Analysis Through Calibrated Evidence Functions.
Teaching Experience:
- 2022-2023: * Computer Science Basics: Boolean Algebra, Logic gate, Floating-point arithmetic (Tutorial B.Sc.), * Computer Science Basics 2: Combinatorial circuits, Sequential circuit, Processor (Tutorial B.Sc.), * Object-oriented programming C++ (Tutorial B.Sc.),
- 2021-2022: * Computer Science Basics: Boolean Algebra, Logic gate, Floating-point arithmetic (Tutorial B.Sc.), * Data Analysis (Tutorial B.Sc.).
- 2020-2021: * Computer Science Basics (Tutorial B.Sc.), * Data Analysis (Tutorial B.Sc.).
- 2019-2020: * Computer Science Basics (Tutorial B.Sc.), * Data Analysis (Tutorial B.Sc.), * Web Development (Tutorial B.Sc.).
Publications
Publications
|
Representing evidence for attribute privacy : bayesian updating, compositional evidence and calibrationOther [cs.OH]. Université d'Avignon, 2023. English. ⟨NNT : 2023AVIG0113⟩
Thèse
tel-04264175
v1
|
|
Explaining a probabilistic prediction on the simplex with Shapley compositionsECAI 2024, Oct 2024, Santiago de Compostela, Spain. ⟨10.3233/FAIA240605⟩
Communication dans un congrès
hal-04687356
v2
|
|
Hiding Speaker’s Sex in Speech Using Zero-Evidence Speaker Representation in an Analysis/Synthesis PipelineICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Jun 2023, Rhodes Island, Greece. pp.1-5, ⟨10.1109/ICASSP49357.2023.10096749⟩
Communication dans un congrès
hal-04264519
v1
|
|
A bridge between features and evidence for binary attribute-driven perfect privacyICASSP 2022, May 2022, Singapore, Singapore
Communication dans un congrès
hal-03375790
v2
|
|
Faire le pont entre l'observation et la preuve : Application au respect de la vie privéeJournées d’Etudes sur la Parole - JEP2022, Jun 2022, Île de Noirmoutier, France
Communication dans un congrès
hal-03813882
v1
|
|
Benchmarking and challenges in security and privacy for voice biometricsSPSC 2021, 1st ISCA Symposium on Security and Privacy in Speech Communication, ISCA, Nov 2021, Magdeburg, Germany. ⟨10.21437/SPSC.2021-11⟩
Communication dans un congrès
hal-03346196
v1
|
|
Adversarial Disentanglement of Speaker Representation for Attribute-Driven Privacy PreservationInterspeech 2021, Aug 2021, Brno, Czech Republic
Communication dans un congrès
hal-03046920
v3
|
|
The Privacy ZEBRA: Zero Evidence Biometric Recognition AssessmentInterspeech 2020, Oct 2021, Shanghai, China. pp.1698-1702, ⟨10.21437/Interspeech.2020-1815⟩
Communication dans un congrès
hal-03555630
v1
|
|
Speech Pseudonymisation Assessment Using Voice Similarity MatricesInterspeech 2020, Oct 2020, Shanghai, China
Communication dans un congrès
hal-02925559
v1
|
|
CGCNN: COMPLEX GABOR CONVOLUTIONAL NEURAL NETWORK ON RAW SPEECHICASSP 2020, May 2020, Barcelona, Spain
Communication dans un congrès
hal-02474746
v1
|
|
Denoising x-vectors for Robust Speaker RecognitionOdyssey 2020 The Speaker and Language Recognition Workshop, Nov 2020, Tokyo, Japan. pp.75-80, ⟨10.21437/Odyssey.2020-11⟩
Communication dans un congrès
hal-02614616
v1
|
|
Introducing the VoicePrivacy initiativeINTERSPEECH 2020, Oct 2020, Shanghai, China
Communication dans un congrès
hal-02562199
v3
|
|
Towards a unified assessment framework of speech pseudonymisationComputer Speech and Language, 2022, 72, pp.101299. ⟨10.1016/j.csl.2021.101299⟩
Article dans une revue
hal-03555462
v1
|
|
The VoicePrivacy 2020 Challenge: Results and findingsComputer Speech and Language, 2022, 74, pp.101362. ⟨10.1016/j.csl.2022.101362⟩
Article dans une revue
hal-03332224
v4
|
|
Compositional discriminant analysis through calibrated evidence functionsThe 10th International Workshop on Compositional Data Analysis (CoDaWork2024), Jun 2024, Girona, Catalonia, Spain
Poster de conférence
hal-04625713
v1
|
|
Supplementary material to the paper The VoicePrivacy 2020 Challenge: Results and findings2022
Pré-publication, Document de travail
hal-03335126
v6
|
|
The VoicePrivacy 2020 Challenge Evaluation Plan[0] LIA - Laboratoire Informatique d'Avignon; MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery; Eurecom [Sophia Antipolis]; University of Edinburgh. 2020
Rapport
hal-03623450
v2
|