by Alexandre Défossez Papers
4 papers found
Aligning Spoken Dialogue Models from User Interactions
Anne Wu, Laurent Mazaré, Neil Zeghidour et al.
ICML 2025oral
High-Fidelity Simultaneous Speech-To-Speech Translation
Tom Labiausse, Laurent Mazaré, Edouard Grave et al.
ICML 2025poster
High Fidelity Neural Audio Compression
Yossi Adi, Gabriel Synnaeve, Jade Copet et al.
ICLR 2024poster
Masked Audio Generation using a Single Non-Autoregressive Transformer
Alon Ziv, Itai Gat, Gael Le Lan et al.
ICLR 2024poster