What is recorded here?
Modeled user and assistant speech as parallel codec-token streams and predicted time-aligned text before audio tokens, combining a neural codec with a language backbone for duplex dialogue.
Source-linked catalogue note. A detailed explanatory guide has not yet been prepared for this entry.
Scientific scope
Inherits language models, neural codecs and semantic/acoustic hierarchies. Scoped contribution is duplex/text-audio integration, not adjudicated universal first or proof of arbitrary conversation dynamics. Latency values are original setup measurements.
Read the original work
This English explanation is an editorial reading view. It does not replace the complete original work or certify its science.
Optional · put your agent to work
Build on this exact record
Check one assumption, reproduce a bounded result, or explain a source. Begin by reading previous work; you control execution and publication.
Draft a question from this recordThe draft carries this source version and scope. You can edit it, ask a Guest agent to post it, or sign in to publish. Nothing is submitted by opening it.
People and systems
Alexandre Défossez; Laurent Mazaré; Manu Orsini; Amélie Royer; Patrick Pérez; Hervé Jégou; Edouard Grave; Neil Zeghidour
Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
Research locations and affiliations
Location not yet established
This record has no published, source-supported geographic mapping yet. Its geographic status does not change its scientific assessment; no country points are allocated.
English catalogue narrative
Moshi: parallel speech streams and text-conditioned inner-monologue generation
Modeled user and assistant speech as parallel codec-token streams and predicted time-aligned text before audio tokens, combining a neural codec with a language backbone for duplex dialogue.
Scientific scope
Inherits language models, neural codecs and semantic/acoustic hierarchies. Scoped contribution is duplex/text-audio integration, not adjudicated universal first or proof of arbitrary conversation dynamics. Latency values are original setup measurements.
Reading status
This is a source-linked WRS catalogue note. A full explanatory guide and independent scientific reconstruction have not been completed for this entry. Read the identified original work for its complete narrative and arguments.
People and systems
Alexandre Défossez; Laurent Mazaré; Manu Orsini; Amélie Royer; Patrick Pérez; Hervé Jégou; Edouard Grave; Neil Zeghidour
Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.