J-Moshi, the first public Japanese full-duplex spoken dialogue model, is built from Moshi and outperforms a Japanese dGSLM baseline on naturalness and meaningfulness.
We used the computational resources of the supercomputer “Flow” at the Information Technology Center, Nagoya University
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Towards a Japanese Full-duplex Spoken Dialogue System
J-Moshi, the first public Japanese full-duplex spoken dialogue model, is built from Moshi and outperforms a Japanese dGSLM baseline on naturalness and meaningfulness.