DuplexJev-4B-Turn

📄 Paper: arXiv:2610.02638 · Code: github.com/adventists-ai/duplexjev

DuplexJev-4B with a turn-taking upgrade. Same size, same serving stack, same prompt format; it decides much better when to speak, when to keep talking and when to stop, while spoken QA, gender and emotion stay where they were.

DuplexJev reads typed, closed-set decisions from speech as a single-token distribution of the LLM: zero decode steps, many questions about the same clip in parallel. This repository is the complete model (Qwen3-ASR-0.6B encoder

• connector + Qwen3-4B, 4.2 B parameters, bf16).

What changed

Starting from DuplexJev-4B we trained the connector together with a small LoRA on the LLM (rank 16 on q/k/v/o, 0.6 % of the parameters; merged into the weights here) on 110 k turn-taking questions rewritten from public corpora, mixed with the original content and paralinguistic data:

Most questions give the system state (the assistant is speaking / idle) and ask for an action (keep talking / stop and listen; reply / keep waiting); the rest ask for the user's turn state.

Results

Paper protocol (single-token readout, PyTorch), % correct. Through vLLM with duplexjev-vllm in the client wording: qa100 77, ZJU-ML 49, gender 87.0, emotion 88.4, Easy-Turn 92.8.

• Easy-Turn: 800-item four-way turn-state test set; the training mix contains the Easy-Turn training split (disjoint from the test set), so this score is in-domain.
• CoDeTT (arXiv 2603.25434): 18 k items, system state given, four actions averaged; zero-shot (no CoDeTT data in training). Our protocol: current utterance as audio, no history. For reference, published results: GPT-4o-audio 66.6 / 71.9, Qwen3-Omni 70.4 / 70.9.
• † TurnBench-dev clips: our own clip-level protocol on the TurnBench development conversations (the official test labels are withheld): end of turn, pause inside a turn, backchannel, floor-taking interruption, noise / channel bleed; mean of four action accuracies. Not comparable with the official TurnBench leaderboard.
• Weakest remaining case: a pause in the middle of a long turn (the model takes the turn too early about half the time).

Serve with vLLM

pip install "vllm[audio]>=0.29" duplexjev-vllm
vllm serve adventists-ai/DuplexJev-4B-Turn --max-model-len 4096

Prompt format, client and decision tables are the same as for DuplexJev-4B; see examples/vllm_client.py. A state-aware question, for example:

The user said: <|audio|>

Question: The user said this while the assistant was speaking. What should the assistant do?

Options:
A. keep talking (backchannel, noise, or not addressed to the assistant)
B. stop and listen (interruption or a new request)

Answer with only the letter of the correct option.

Limitations

• Decides on one clip at a time; it is not a streaming end-of-turn detector by itself (call it at each pause).
• Pauses inside long turns are still often taken as the end of the turn.
• Emotion labels come from acted corpora; do not use the outputs to make decisions about individuals.

License

CC BY-NC 4.0, research use only (emotion data ESD is research-only; SmoothConv is CC BY-NC). Base models keep their licences: Qwen3-4B and Qwen3-ASR-0.6B are Apache-2.0 (Alibaba Cloud). The LLM weights here are Qwen3-4B with a LoRA merged in.

Citation

@misc{jin2026duplexjev,
  title         = {Batched Speech Decisions Without Decoding: Single-Token Supervision Lets a Frozen {LLM} Hear Beyond the Transcript},
  author        = {Jin, Jie and Ma, Ziyin and Yin, Min and Chen, Jinyu and Song, Haigang and Pang, Zhikun and Zhang, Xiaowen},
  year          = {2026},
  eprint        = {2610.02638},
  archivePrefix = {arXiv},
  note          = {Submitted to IEEE ICASSP 2027}
}

Built by Adventists.ai. Claude (Anthropic) assisted with code.