CORTEXA
← Browse
arxivcs.CLcs.AI2026-07-01

TurnNat: Automatic Evaluation of Turn-Taking Naturalness in Dyadic Spoken Dialogue

Hao Zhang, Thomas Thebaud, Georgi Tinchev, Venkatesh Ravichandran, Laureano Moro-Velazquez

Turn-taking naturalness is central to full-duplex spoken dialogue systems, yet its automatic evaluation remains limited. Existing evaluations often rely on human judgments or behavior-specific timing metrics, making it difficult to compare heterogeneous timing failures within a unified framework. We propose TurnNat, a likelihood-based framework for automatic turn-taking naturalness evaluation in two-channel spoken dialogue. A causal turn-taking prediction model trained on natural conversations estimates future two-speaker voice-activity states, and the negative log-likelihood (NLL) of the observed future activity measures timing atypicality. TurnNat pools frame-level NLLs over turn-taking boundary units (TBUs) extracted from utterance onsets and offsets, and aggregates mean and tail TBU scores into a dialogue-level naturalness score. We further construct a controlled perturbation benchmark of paired natural and perturbed dialogue clips, validated by human naturalness judgments. Experiments on this benchmark show that TurnNat successfully identifies unnatural turn-taking perturbations across heterogeneous timing failures.

View free PDFSource page

Related papers

arxivcs.ROcs.AIcs.CL2026-07-08

Multimodal Voice Activity Projection for Turn-Taking in Social Robots with Voice-Activity-Related Pretrained Encoders

Antonio Cano, Guillermo Pérez, Luis Merino, Randy Gomez

Turn-taking prediction is a key requirement for social robots involved in human-human interaction, particularly in mediator settings, where the robot must anticipate conversational dynamics rather than merely react to pauses. This work presents a Multimodal Voice Activity Project…

View free PDFSource page
arxivcs.CLcs.AIeess.AS2026-07-06

SPEARBench: A Benchmark for Naturalness Evaluation in Streaming Speech-to-Speech Language Models

Thomas Thebaud, Yuzhe Wang, Hao Zhang, Sathvik Manikantan Napa Ugandhar, Ashish Hallur, Georgi Tinchev, et al.

Streaming speech-to-speech language models aim to answer spoken queries directly with synthetic speech. However, standard speech and text benchmarks do not capture whether these systems behave naturally in conversations, where timing, turn-taking, prosody, interpersonal stance, l…

View free PDFSource page
arxivcs.CLcs.AIcs.HC2026-07-17

On the Structure of Address in Multi-Party Dialogue: From Discrete Labels to Continuous Levels

Taiga Mori, Koji Inoue, Divesh Lala, Tatsuya Kawahara

In multi-party dialogues between a dialogue system and multiple users, identifying to whom an utterance is addressed is a key challenge. Prior work has typically treated addressee detection as a multi-class classification task, selecting a single label representing an individual…

View free PDFSource page
arxivcs.AIcs.CLcs.LO2026-06-30

Beyond Compilation: Evaluating Faithful Natural-Language-to-Lean Statement Formalization

Ke Zhang, Patricio Gallardo Candela, Sudhir Murthy, Yi Xie, Zhi Wang, Maziar Raissi

Theorem-proving benchmarks evaluate proof search against fixed formal statements, but natural-language-to-Lean formalization must generate the formal statement itself. In this setting, compilation is only a validity check: a Lean declaration may type-check while omitting hypothes…

View free PDFSource page
arxivcs.CLcs.AI2026-07-21

MedDDC-Eval: Diagnosis-Decoupled Evaluation of Multi-Turn Medical Consultation Agents

Guofeng Zhang, Yizeng Quan, Huaiyi Fang, Jianwei Lv, Jinyao Liu, Xunxu Duan, et al.

Multi-turn medical consultation agents must decide what to ask, adapt to patient responses, and determine when the collected evidence is sufficient. However, coupled evaluation conflates the quality of the policy-elicited history with policy-specific terminal diagnosis generation…

View free PDFSource page
arxivcs.CLcs.AI2026-07-04

Consistent but Miscalibrated: Evaluating LLM Limitations for Risk Communication in Natural Language

Diego Cerda-Mardini, Sarath Chandar, Sreenath Madathil

LLMs are increasingly deployed as post-hoc explainers of AI-generated outputs, yet it remains unclear whether they can reliably communicate probabilistic information in natural language. For this role to be viable, models must produce identical verbal descriptions for identical i…

View free PDFSource page