Skip to main content
Search

# Full-duplex voice agents

1 related articles

Subscribe to updates
  1. arXiv

    Voice agents skip token-by-token decoding: a frozen LLM reads one hidden state, answering 80 decisions on eight utterances in about 0.1 s

    Full-duplex voice agents make many small closed decisions, and current systems answer them by slow autoregressive decoding. DuplexJev 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, decoding nothing; 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%); a cross-attention connector brings gender and emotion accuracy to 90% (from 55% and 28%) while spoken QA drops only one point (83% to 82%).

You’re all caught up