Search Results for author: Marie Tahon

Found 16 papers, 1 papers with code

Overlaps and Gender Analysis in the Context of Broadcast Media

no code implementations LREC 2022 Martin Lebourdais, Marie Tahon, Antoine Laurent, Sylvain Meignier, Anthony Larcher

Our main goal is to study the interactions between speakers according to their gender and role in broadcast media.

Unsupervised Multiple Domain Translation through Controlled Disentanglement in Variational Autoencoder

1 code implementation17 Jan 2024 Antonio Almudévar, Théo Mariotte, Alfonso Ortega, Marie Tahon

One of this latent variables is imposed to depend exclusively on the domain, while the other one must depend on the rest of the variability factors of the data.

Disentanglement Translation

Acoustic and linguistic representations for speech continuous emotion recognition in call center conversations

no code implementations6 Oct 2023 Manon Macary, Marie Tahon, Yannick Estève, Daniel Luzzati

In the context of telephone conversations, we can break down the audio information into acoustic and linguistic by using the speech signal and its transcription.

Emotion Recognition Transfer Learning

Evaluation of Speaker Anonymization on Emotional Speech

no code implementations15 Apr 2023 Hubert Nourtel, Pierre Champion, Denis Jouvet, Anthony Larcher, Marie Tahon

This paper studies the impact of the speaker anonymization baseline system of the VPC on emotional information present in speech utterances.

Automatic Speech Recognition Emotion Recognition +3

Training speech emotion classifier without categorical annotations

no code implementations14 Oct 2022 Meysam Shamsi, Marie Tahon

There are two paradigms of emotion representation, categorical labeling and dimensional description in continuous space.

Classification Emotion Recognition +1

Overlapped speech and gender detection with WavLM pre-trained features

no code implementations9 Sep 2022 Martin Lebourdais, Marie Tahon, Antoine Laurent, Sylvain Meignier

This article focuses on overlapped speech and gender detection in order to study interactions between women and men in French audiovisual media (Gender Equality Monitoring project).

On the use of Self-supervised Pre-trained Acoustic and Linguistic Features for Continuous Speech Emotion Recognition

no code implementations18 Nov 2020 Manon Macary, Marie Tahon, Yannick Estève, Anthony Rousseau

Pre-training for feature extraction is an increasingly studied approach to get better continuous representations of audio and text content.

Speech Emotion Recognition

Pr\'ediction continue de la satisfaction et de la frustration dans des conversations de centre d'appels (AlloSat : A New Call Center French Corpus for Affect Analysis)

no code implementations JEPTALNRECITAL 2020 Manon Macary, Marie Tahon, Yannick Est{\`e}ve, Anthony Rousseau

AlloSat regroupe 303 conversations pour un total d{'}environ 37 heures d{'}audio, toutes enregistr{\'e}es dans des environnements r{\'e}els, collect{\'e}es par Allo-Media (une soci{\'e}t{\'e} sp{\'e}cialis{\'e}e dans l{'}analyse automatique d{'}appels).

AlloSat: A New Call Center French Corpus for Satisfaction and Frustration Analysis

no code implementations LREC 2020 Manon Macary, Marie Tahon, Yannick Est{\`e}ve, Anthony Rousseau

We present a new corpus, named AlloSat, composed of real-life call center conversations in French that is continuously annotated in frustration and satisfaction.

Towards Interactive Annotation for Hesitation in Conversational Speech

no code implementations LREC 2020 Jane Wottawa, Marie Tahon, Apolline Marin, Nicolas Audibert

Furthermore, regression models were trained in order to allow automatic prediction of hesitation for speech chunks that do not have a manual annotation.

Corpus of Children Voices for Mid-level Markers and Affect Bursts Analysis

no code implementations LREC 2012 Marie Tahon, Agnes Delaborde, Laurence Devillers

This article presents a corpus featuring children playing games in interaction with the humanoid robot Nao: children have to express emotions in the course of a storytelling by the robot.

Cannot find the paper you are looking for? You can Submit a new open access paper.