Picture for Marc-André Carbonneau

Marc-André Carbonneau

Spoken-Term Discovery using Discrete Speech Units

Add code
Aug 26, 2024
Viaarxiv icon

BinaryAlign: Word Alignment as Binary Sequence Labeling

Add code
Jul 16, 2024
Viaarxiv icon

Zero-shot Cross-Lingual Transfer for Synthetic Data Generation in Grammatical Error Detection

Add code
Jul 16, 2024
Viaarxiv icon

UPose3D: Uncertainty-Aware 3D Human Pose Estimation with Cross-View and Temporal Cues

Add code
Apr 23, 2024
Viaarxiv icon

EDMSound: Spectrogram Based Diffusion Models for Efficient and High-Quality Audio Synthesis

Add code
Nov 18, 2023
Viaarxiv icon

Rhythm Modeling for Voice Conversion

Add code
Jul 12, 2023
Viaarxiv icon

ZeroEGGS: Zero-shot Example-based Gesture Generation from Speech

Add code
Sep 23, 2022
Figure 1 for ZeroEGGS: Zero-shot Example-based Gesture Generation from Speech
Figure 2 for ZeroEGGS: Zero-shot Example-based Gesture Generation from Speech
Figure 3 for ZeroEGGS: Zero-shot Example-based Gesture Generation from Speech
Figure 4 for ZeroEGGS: Zero-shot Example-based Gesture Generation from Speech
Viaarxiv icon

A Comparison of Discrete and Soft Speech Units for Improved Voice Conversion

Add code
Nov 03, 2021
Figure 1 for A Comparison of Discrete and Soft Speech Units for Improved Voice Conversion
Figure 2 for A Comparison of Discrete and Soft Speech Units for Improved Voice Conversion
Figure 3 for A Comparison of Discrete and Soft Speech Units for Improved Voice Conversion
Figure 4 for A Comparison of Discrete and Soft Speech Units for Improved Voice Conversion
Viaarxiv icon

Daft-Exprt: Robust Prosody Transfer Across Speakers for Expressive Speech Synthesis

Add code
Aug 04, 2021
Figure 1 for Daft-Exprt: Robust Prosody Transfer Across Speakers for Expressive Speech Synthesis
Figure 2 for Daft-Exprt: Robust Prosody Transfer Across Speakers for Expressive Speech Synthesis
Figure 3 for Daft-Exprt: Robust Prosody Transfer Across Speakers for Expressive Speech Synthesis
Figure 4 for Daft-Exprt: Robust Prosody Transfer Across Speakers for Expressive Speech Synthesis
Viaarxiv icon

Energy Disaggregation using Variational Autoencoders

Add code
Mar 22, 2021
Figure 1 for Energy Disaggregation using Variational Autoencoders
Figure 2 for Energy Disaggregation using Variational Autoencoders
Figure 3 for Energy Disaggregation using Variational Autoencoders
Figure 4 for Energy Disaggregation using Variational Autoencoders
Viaarxiv icon