activity
20222026
most citedZero-shot text-to-speech synthesis conditioned using self-supervised speech representation model

9 citations · 9 across the 5 of their papers we have counts for

collaborators
Showing cs.CLShow all

1 paper · 1 filter

cs.CL2026

M3-DuplexBench: A Multi-Turn, Multilingual, Multidomain Benchmark for Full-Duplex Spoken Dialogue Models

Ryo Fukuda, Atsushi Ando, Hiroki Kanagawa +4

Full-duplex spoken dialogue systems (FDSDSs) can listen while speaking, enabling natural conversational behaviors such as smooth turn-taking, backchannel handling, and user barge-i…