Picture for Emmanuel Dupoux

Emmanuel Dupoux

LSCP, CoML

Countering Reward Over-optimization in LLM with Demonstration-Guided Reinforcement Learning

Add code
Apr 30, 2024
Viaarxiv icon

Language Evolution with Deep Learning

Add code
Mar 18, 2024
Figure 1 for Language Evolution with Deep Learning
Figure 2 for Language Evolution with Deep Learning
Figure 3 for Language Evolution with Deep Learning
Figure 4 for Language Evolution with Deep Learning
Viaarxiv icon

SpiRit-LM: Interleaved Spoken and Written Language Model

Add code
Feb 08, 2024
Viaarxiv icon

EmphAssess : a Prosodic Benchmark on Assessing Emphasis Transfer in Speech-to-Speech Models

Add code
Dec 21, 2023
Viaarxiv icon

WorldSense: A Synthetic Benchmark for Grounded Reasoning in Large Language Models

Add code
Nov 27, 2023
Viaarxiv icon

XLS-R fine-tuning on noisy word boundaries for unsupervised speech segmentation into words

Add code
Oct 08, 2023
Figure 1 for XLS-R fine-tuning on noisy word boundaries for unsupervised speech segmentation into words
Figure 2 for XLS-R fine-tuning on noisy word boundaries for unsupervised speech segmentation into words
Figure 3 for XLS-R fine-tuning on noisy word boundaries for unsupervised speech segmentation into words
Figure 4 for XLS-R fine-tuning on noisy word boundaries for unsupervised speech segmentation into words
Viaarxiv icon

Generative Spoken Language Model based on continuous word-sized audio tokens

Add code
Oct 08, 2023
Figure 1 for Generative Spoken Language Model based on continuous word-sized audio tokens
Figure 2 for Generative Spoken Language Model based on continuous word-sized audio tokens
Figure 3 for Generative Spoken Language Model based on continuous word-sized audio tokens
Figure 4 for Generative Spoken Language Model based on continuous word-sized audio tokens
Viaarxiv icon

Low-Resource Self-Supervised Learning with SSL-Enhanced TTS

Sep 29, 2023
Figure 1 for Low-Resource Self-Supervised Learning with SSL-Enhanced TTS
Figure 2 for Low-Resource Self-Supervised Learning with SSL-Enhanced TTS
Figure 3 for Low-Resource Self-Supervised Learning with SSL-Enhanced TTS
Figure 4 for Low-Resource Self-Supervised Learning with SSL-Enhanced TTS
Viaarxiv icon

EXPRESSO: A Benchmark and Analysis of Discrete Expressive Speech Resynthesis

Add code
Aug 10, 2023
Figure 1 for EXPRESSO: A Benchmark and Analysis of Discrete Expressive Speech Resynthesis
Figure 2 for EXPRESSO: A Benchmark and Analysis of Discrete Expressive Speech Resynthesis
Figure 3 for EXPRESSO: A Benchmark and Analysis of Discrete Expressive Speech Resynthesis
Figure 4 for EXPRESSO: A Benchmark and Analysis of Discrete Expressive Speech Resynthesis
Viaarxiv icon

BabySLM: language-acquisition-friendly benchmark of self-supervised spoken language models

Add code
Jun 08, 2023
Figure 1 for BabySLM: language-acquisition-friendly benchmark of self-supervised spoken language models
Figure 2 for BabySLM: language-acquisition-friendly benchmark of self-supervised spoken language models
Figure 3 for BabySLM: language-acquisition-friendly benchmark of self-supervised spoken language models
Figure 4 for BabySLM: language-acquisition-friendly benchmark of self-supervised spoken language models
Viaarxiv icon