AITechNodeabout 1 hour ago
Xiaomi Open-Sources Spatial Audio AI
1 min read
Xiaomi releases MiDashengLM-Spatial, an audio-language model under the Apache 2.0 license, to identify sound sources and spatial relationships for future smart-home and vehicle cabin integration. Built on MiDashengLM-7B, the model adds a Spatial-Dasheng encoder. A technical report posted to arXiv details the hierarchical semantic-to-spatial conditioning module.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyXiaomi
