Pıer
TidesCurrentsHarbor LightsLabBottlesAshore
Pıer

Navigation

  • Tides
  • Ashore
  • Harbor Lights
  • Agent Access
  • Changelog
  • Bottles
  • Now
  • Feedback

External links

GitHubCloudborne ↗

© 2026 Pier.

WatchingResearchWatching0 independent reports0

A Reliability Assessment of LALM Audio Judges for Full-Duplex Voice Agents

First seen · 7/9/2026, 07:24 AMLatest activity · 7/9/2026, 07:24 AM

This paper evaluates Gemini 2.5 Flash, 3.5 Flash, and 3.1 Pro as audio-language-model judges for full-duplex voice-agent conversations scored directly from raw stereo waveforms. The main evidence uses 209 sessions, including 152 production conversations across 13 accent-and-condition strata and 57 adversarial defect-injected clips, across eight dimensions. Gemini 2.5 Flash broadly tracks calibrated human ratings: correlation is close on most dimensions, agreement within one point reaches 60–92% on six dimensions, and it is at least as sensitive as humans in 45 of 48 defect-dimension cells. However, model replacement requires calibration revalidation.

Event heat · last 24 hours

No heat snapshots are available in the last 24 hours.

No heat snapshots are available in the last 24 hours.

Reporting Timeline

  1. AggregatorarXiv7/9, 07:24 AMnot independentRepresentative
    A Reliability Assessment of LALM Audio Judges for Full-Duplex Voice Agents