benchmark · first seen 13 Oct 2026
full-duplex spoken dialogue benchmark
Evaluation suite measuring how well spoken models take appropriate interaction actions in conversation.
Mentions per week
PapersCodeDiscussion
Earliest sources
- DuplexAct: How Interactive Are Frontier Full-Duplex Spoken Language Models?Papers · 13 Oct 2026 · Jiaheng Dong, Shihong Tan, Gongping Huang, Jean Honorio, Abhirup Ghosh, Ting Dan…
Latest sources
- DuplexAct: How Interactive Are Frontier Full-Duplex Spoken Language Models?Papers · 13 Oct 2026 · Jiaheng Dong, Shihong Tan, Gongping Huang, Jean Honorio, Abhirup Ghosh, Ting Dan…