Skip to main content
Search

# Turn-taking Dynamics

1 related articles

Subscribe to updates
  1. arXiv

    Two separately recorded voice tracks become one conversation: a neural scheduler learns only timing while a back-channel predictor decides where listeners interject

    In game voice production, the two speakers' lines are usually recorded separately in the booth, and splicing them yields stiff turn changes with no listener back-channels. This pipeline first uses a back-channel predictor to decide whether each line invites an interjection and of which class, then a neural scheduler jointly places onset times on both channels, inserting pauses and overlap. On the Fisher corpus the scheduler stays closer to ground-truth turn statistics than Moshi, NTPP and other baselines on most of four metrics; on Full-Duplex Bench it produces back-channels at 0.062 per second with a Jensen-Shannon divergence of 0.644 from natural back-channel timing.

You’re all caught up