Doubao's duplex end-to-end voice model powers near-human in-car chat
xiaohu · x · 2026-09-17
The Doubao cockpit assistant relies on a duplex end-to-end voice model, enabling natural, fluid voice interaction that feels close to talking with a human — the key technical differentiator from traditional in-car voice systems.
More from Embodied
- Key open challenges for VLAs: language, evaluation, deployment, causal reasoning — abursuc · 2026-09-17
- LADA: latent actions imitate language from few observation-language pairs — abursuc · 2026-09-17
- A Primer on Latent Action Models From the #ssad2026 Talks — abursuc · 2026-09-17
- FIVE-VLA Runs Driving With Just 640M Parameters, 7.5x More Efficient Than SimLingo — abursuc · 2026-09-17
- Function-Preserving Shape Deformation Enables Zero-Shot Real-to-Sim-to-Real Robot Manipulation — zhenjun_zhao · 2026-09-17
- ActiveScale Trains Robots to Actively Perceive Using 1000 Hours of Egocentric Data — zhenjun_zhao · 2026-09-17