Batched Speech Decisions Without Decoding: Single-Token Supervision Lets a Frozen LLM Hear Beyond the Transcript
Full-duplex voice agents make many small, closed decisions, which current systems answer by slow autoregressive decoding. We propose DuplexJev, which feeds ASR-encoder hidden states through a small connector into a frozen LLM and reads each question as a single-token distribution over its options. Nothing is decoded, and an 8-GPU node answers 80 decisions about eight utterances in about 0.1 s. With a last-layer connector, spoken QA stays close to reading the transcript (90% vs. 91%). DuplexJev also hears the speaker: gender and emotion accuracy both reach 90% (from 55% and 28%) with a cross-attention connector, whose spoken QA drops by only 1 point (83% to 82%). We train decisions with cr...
| Authors | Jie Jin, Ziyin Ma, Min Yin et al. |
|---|---|
| Primary category | cs.AI |
| Published | 2 October 2026 |
| Last updated at source | 2 October 2026 |
Popularity, last 4 days
0 now. Counts as reported by the source, snapshotted daily by Silytics.
Connected in the knowledge graph
- adventists-ai/DuplexJev-32B-ParaModel · cited by
Recent changes
- 16 Oct 2026 Description: Full-duplex voice agents make many small, closed decisions, which current systems answer by slow autoregressive decoding. We propose DuplexJev, which feeds ASR-encoder hidden states through a small connector into a frozen LLM and reads each → Full-duplex voice agents make many small, closed decisions, which current systems answer by slow autoregressive decoding. We propose DuplexJev, which feeds ASR-encoder hidden states through a small connector into a frozen LLM and reads each
- 16 Oct 2026 Topics added cs.AI removed hf-daily-papers, asr-encoder hidden states, frozen llm, cross-attention connector, cross-entropy, transcript distillation, full-duplex serving
Changes detected by Silytics between refreshes of the source.
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 18 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.