arXiv AI
DuplexAct: How Interactive Are Frontier Full-Duplex Spoken Language Models?
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computation and Language
Oct 12
M3-DuplexBench: A Multi-Turn, Multilingual, Multidomain Benchmark for Full-Duplex Spoken Dialogue Models
M3-DuplexBench is a new benchmark designed to evaluate full‑duplex spoken dialogue systems (FDSDSs) that can listen while speaking. It covers multi‑turn interactions in both English and Japanese across casual conversation and question‑answering domains, jointly assessing interaction timing and response content. The benchmark also offers a reference‑conditioned setting to test sensitivity to dialogue history and trajectory mismatch.
arXiv Computation and Language
Oct 1
DuplexAct-Bench: Broadening Full-Duplex Speech Evaluation toward Proactive Interaction across Diverse Behavioral Requirements
arXiv:2609.39446v1 Announce Type: new Abstract: Existing full-duplex speech benchmarks cover only subsets of real-time interaction behaviors, often under limited contextual conditions. We introduce D...
arXiv AI
Sep 1
Enabling Proactive Spoken Turns via a Generalized Style-Aware Full-Duplex Framework
arXiv:2608.28630v1 Announce Type: cross Abstract: Compared with half-duplex dialogue systems where the system waits for user turn completion before it responds, natural full-duplex dialogue systems r...
arXiv Computation and Language
Aug 27
TurnBench: A Multi-Domain Benchmark for Turn-Taking Dynamics in Spoken Dialogue
TurnBench is a new multi‑domain benchmark for evaluating turn‑taking dynamics in spoken dialogue. It comprises a 30‑hour hand‑labeled corpus of dyadic human conversations, a standardized evaluation protocol for end‑of‑turn and interruption detection, and covers six distinct interaction styles with triple annotation. The benchmark also provides a 104‑hour training set, a public leaderboard, and an interactive dataset viewer at https://turnbench.sesame.com.
arXiv Computation and Language
Sep 14
SteerDuplex: Steerable Duplex Speech Dialogue Models
SteerDuplex is a full‑duplex speech dialogue model that can be steered along attributes such as tone, persona, speaking rate, and voice style in response to user instructions. The authors introduce a taxonomy of text‑ and audio‑based steerability, identify gaps in existing models, and fine‑tune a Moshi‑based model with reinforcement learning to improve timing and response continuity. They also present SteerBench, a benchmark of 390 spoken prompts and 1,067 human‑authored rubrics, showing significant gains in audio‑steering pass rates and interruption handling compared to open baselines.
arXiv Computation and Language
Sep 1
Multi-Faceted Interactivity Alignment in Full-Duplex Speech Models
arXiv:2606.11167v2 Announce Type: replace Abstract: Full-duplex spoken dialogue models can listen and speak simultaneously, making them a promising architecture for natural conversation. However, cur...