Full‑duplex speech models can listen and speak simultaneously, but they struggle to decide when to speak. Experiments with five model families show that being addressed or encountering silence are reliable triggers, whereas cues like false facts or hazards are not. Even when models answer questions, they rarely challenge false claims or warn about danger, revealing a gap in content understanding and intervention decisions.
Full-duplex speech models listen and speak at once, promising always-on assistants. Yet they must also decide when they should speak. Human listeners speak when addressed or when the speaker stops, bu...
The study evaluates conversational speech models by placing them at 427 pauses and 482 turn ends from 176 unscripted conversations, scoring their responses on timing, latency, length, wording, and recall of recent dialogue. Hosted APIs (GPT Realtime, Gemini 3.1 Flash Live, Grok Voice) respond at almost every pause, with latency ranging from 1–4 s for silence-based endpointers and about 8 s for semantic turn detection, while full‑duplex models (PersonaPlex, Moshi) remain silent more often and can interrupt within human reaction time. Recall rates vary: hosted systems remember 41–60 % of facts under a Claude Opus 5.5 judge and 19–26 % with a strict word matcher; full‑duplex models recall 17–22 % and 12–15 % respectively.
arXiv:2608. 19515v1 Announce Type: new Abstract: Prosodic cues can convey task-relevant information that alters the trajectory and outcome of a task-oriented dialogue, even when the words themselves remain unchanged.
The paper introduces a pipeline that generates intent‑labeled, two‑channel conversational speech from relational event lists, enabling controlled synthesis of full‑duplex dialogue with 42 phenomena across eight families in English and Mandarin. By having an LLM author each event’s speaker, text, conversational act, and attachment, and then aligning and timing these events independently, the system produces diverse, realistic turn‑taking signals. Experiments show that models trained on this synthetic corpus achieve higher floor‑occupancy accuracy and better start‑speaking/listening F1 scores compared to models trained on prior data.
Prosodic cues can convey task-relevant information that alters the trajectory and outcome of a task-oriented dialogue, even when the words themselves remain unchanged. Yet existing benchmarks typically evaluate prosodic perception, response appropriateness, and task-oriented dialogue in isolation, making it difficult to test whether prosodic evidence changes downstream decisions.
arXiv:2609.13117v1 Announce Type: new Abstract: Full-duplex evaluation often emphasizes whether an agent keeps speaking or stops. That binary cannot express a third response humans use routinely: con...
arXiv:2609.27372v1 Announce Type: cross Abstract: Benchmarks for full-duplex spoken dialogue models score turn-taking with binary fixed-window rules that reward immediate response or silence by compl...
arXiv:2609.13445v1 Announce Type: new Abstract: Speech-to-speech LLMs like Moshi, and its derivative PersonaPlex, can listen and speak concurrently through full-duplex generation. However, they can b...
arXiv:2608.29241v1 Announce Type: new Abstract: Clinical voice agents are now deployed in routine care, where real patients do not wait their turn: they interrupt. These systems typically use a casca...
arXiv:2610.32349v1 Announce Type: new Abstract: Full-duplex speech models listen and speak at the same time, which makes them promising for natural, open-ended conversation. But can they sustain a co...
arXiv:2610.20172v1 Announce Type: cross Abstract: Full-duplex speech systems must decide when to enter, hold, or relinquish the conversational floor, even as multiple speakers overlap or backchannel...
The paper introduces ContraTalk, a benchmark that tests whether dialogue models truly use acoustic cues or rely on transcript shortcuts. It formalizes cross‑modal disagreement, creates conflict and consistent QA examples, and proposes an Audio Twin representation to expose acoustic evidence to models. Experiments show that while text‑only LLMs perform well on consistent cases, they falter on conflict cases, and AudioLLMs only partially mitigate this issue.