5 papers
TokenChain: A Discrete Speech Chain via Semantic Token Modeling
Mingxuan Wang, Satoshi Nakamura
Machine Speech Chain, simulating the human perception-production loop, proves effective in jointly improving ASR and TTS. We propose TokenChain, a fully discrete speech chain coupl…
Soliton-type metrics associated with weighted CSCK metrics on Fano manifolds
Satoshi Nakamura
We study weighted constant scalar curvature Kähler metrics, introduced by Lahdili as -CSCK metrics, on Fano manifolds and their relationship with soliton-type metrics. In t…
Understanding Mental States to Guide Social Influence in Multi-Person Group Dialogue
Zhichao Liang, Satoshi Nakamura
Existing dynamic Theory of Mind (ToM) benchmarks mostly place language models in a passive role: the model reads a sequence of connected scenarios and reports what people believe,…
StressTransfer: Stress-Aware Speech-to-Speech Translation with Emphasis Preservation
Xi Chen, Yuchen Song, Satoshi Nakamura
We propose a stress-aware speech-to-speech translation (S2ST) system that preserves word-level emphasis by leveraging LLMs for cross-lingual emphasis conversion. Our method transla…
Continuity method for the Mabuchi soliton on the extremal Fano manifolds
Tomoyuki Hisamoto, Satoshi Nakamura
We run the continuity method for Mabuchi's generalization of Kähler-Einstein metrics, assuming the existence of an extremal Kähler metric. It gives an analytic proof (without min…