Moshi is the first real-time full-duplex spoken large language model that casts dialogue as speech-to-speech generation using parallel audio streams and an inner monologue of time-aligned text tokens.
The zero resource speech challenge 2021: Spoken language modelling
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
SpidR-Adapt uses meta-learning with a first-order bi-level optimization heuristic to adapt speech representations to new languages with less than 1 hour of data, achieving 100x better efficiency than standard training.
Introduces INSV-A automated screening benchmark for Pashto TTS systems reporting WER, script fidelity, and LID results across five systems on FLEURS and Common Voice prompts.
citing papers explorer
-
Moshi: a speech-text foundation model for real-time dialogue
Moshi is the first real-time full-duplex spoken large language model that casts dialogue as speech-to-speech generation using parallel audio streams and an inner monologue of time-aligned text tokens.
-
SpidR-Adapt: A Universal Speech Representation Model for Few-Shot Adaptation
SpidR-Adapt uses meta-learning with a first-order bi-level optimization heuristic to adapt speech representations to new languages with less than 1 hour of data, achieving 100x better efficiency than standard training.
-
PashtoTTS-Bench: automated screening for low-resource non-Latin-script text-to-speech
Introduces INSV-A automated screening benchmark for Pashto TTS systems reporting WER, script fidelity, and LID results across five systems on FLEURS and Common Voice prompts.