AIConfPaper
← Search

Fabien Ringeval

8 accepted papers

2024

Jargon: A Suite of Language Models and Evaluation Tasks for French Specialized Domains

Vincent Segonne, Aidan Mannion, Laura Cristina Alonzo Canul, Alexandre Daniel Audibert, Xingyu Liu, Cécile Macaire +20
COLING 2024main

Pretrained Language Models (PLMs) are the de facto backbone of most state-of-the-art NLP systems. In this paper, we introduce a family of domain-specific pretrained PLMs for French, focusing on three important domains: transcribed speech, medicine, and law. We use a transformer architecture based on…

Cited by 3Source ↗PDF ↗code ↗Scholar ↗
2024

PSentScore: Evaluating Sentiment Polarity in Dialogue Summarization

Yongxin Zhou, Fabien Ringeval, François Portet
COLING 2024main

Automatic dialogue summarization is a well-established task with the goal of distilling the most crucial information from human conversations into concise textual summaries. However, most existing research has predominantly focused on summarizing factual information, neglecting the affective content…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2021

Task Agnostic and Task Specific Self-Supervised Learning from Speech with LeBenchmark

Solène Evain, Ha Nguyen, Hang Le, Marcely Zanon Boito, Salima Mdhaffar, Sina Alisamir +12
NeurIPS 2021poster

Self-Supervised Learning (SSL) has yielded remarkable improvements in many different domains including computer vision, natural language processing and speech processing by leveraging large amounts of unlabeled data. In the specific context of speech, however, and despite promising results, there ex…

Cited by 41Source ↗Scholar ↗
2018

Towards Conditional Adversarial Training for Predicting Emotions from Speech

Jing Han, Zixing Zhang, Zhao Ren, Fabien Ringeval, Björn W. Schuller
ICASSP 2018accepted

Motivated by the encouraging results recently obtained by generative adversarial networks in various image processing tasks, we propose a conditional adversarial training framework to predict dimensional representations of emotion, i. e., arousal and valence, from speech signals. The framework consi…

Cited by 0Source ↗Scholar ↗
2017

Prediction-based learning for continuous emotion recognition in speech

Jing Han, Zixing Zhang, Fabien Ringeval, Björn W. Schuller
ICASSP 2017accepted

In this paper, a prediction-based learning framework is proposed for a continuous prediction task of emotion recognition from speech, which is one of the key components of affective computing in multimedia. The main goal of this framework is to utmost exploit the individual advantages of different r…

Cited by 0Source ↗Scholar ↗
2017

Reconstruction-error-based learning for continuous emotion recognition in speech

Jing Han, Zixing Zhang, Fabien Ringeval, Björn W. Schuller
ICASSP 2017accepted

To advance the performance of continuous emotion recognition from speech, we introduce a reconstruction-error-based (RE-based) learning framework with memory-enhanced Recurrent Neural Networks (RNN). In the framework, two successive RNN models are adopted, where the first model is used as an autoenc…

Cited by 0Source ↗Scholar ↗
2016

Adieu features? End-to-end speech emotion recognition using a deep convolutional recurrent network

George Trigeorgis, Fabien Ringeval, Raymond Brueckner, Erik Marchi, Mihalis A. Nicolaou, Björn W. Schuller +1
ICASSP 2016accepted

The automatic recognition of spontaneous emotions from speech is a challenging task. On the one hand, acoustic features need to be robust enough to capture the emotional content for various styles of speaking, and while on the other, machine learning algorithms need to be insensitive to outliers whi…

Cited by 0Source ↗Scholar ↗
2016

Enhanced semi-supervised learning for multimodal emotion recognition

Zixing Zhang, Fabien Ringeval, Bin Dong, Eduardo Coutinho, Erik Marchi, Björn W. Schuller
ICASSP 2016accepted

Semi-Supervised Learning (SSL) techniques have found many applications where labeled data is scarce and/or expensive to obtain. However, SSL suffers from various inherent limitations that limit its performance in practical applications. A central problem is that the low performance that a classifier…

Cited by 0Source ↗Scholar ↗