Atlas / Reports / Detail
Moshi: a speech-text foundation model for real-time dialogue
Speech Language Models report from Kyutai with 7 connected researchers in the LLMpeople atlas.
Connected researchers
Researcher
1 reports
Alexandre Defossez
Kyutai
Researcher at Kyutai and coauthor of the Moshi: a speech-text foundation model for real-time dialogue.
Researcher
1 reports
Laurent Mazaré
Kyutai
Researcher at Kyutai and coauthor of the Moshi: a speech-text foundation model for real-time dialogue.
Researcher
2 reports
Manu Orsini
Kyutai
Researcher at Kyutai and coauthor of the Moshi: a speech-text foundation model for real-time dialogue.
Researcher
1 reports
Amelie Royer
Kyutai
Amelie Royer is a research scientist at Kyutai in Paris working on efficient large models and speech-language systems. Before joining Kyutai in June 2024, she spent three years at Qualcomm AI Research working on efficient and multimodal machine learning. She earned a PhD in computer science from ENS Paris-Saclay and LIP6 in 2021 after a master's in applied mathematics from ENS Paris-Saclay.
Researcher
1 reports
Eugene Kharitonov
Kyutai
Researcher at Kyutai and coauthor of the Moshi: a speech-text foundation model for real-time dialogue.
Researcher
1 reports
Patrick Simon
Kyutai
Researcher at Kyutai and coauthor of the Moshi: a speech-text foundation model for real-time dialogue.
Researcher
1 reports
Yossi Adi
Kyutai
Researcher at Kyutai and coauthor of the Moshi: a speech-text foundation model for real-time dialogue.