Xiaomi open-sources MiDashengLM-Spatial audio model for sound direction and distance
Overview
Xiaomi has released MiDashengLM-Spatial, an audio model of about 8 billion parameters, as open source under the Apache 2.0 license, which permits research and commercial use.
The model describes sounds and reasons about their direction, distance and movement from binaural, two-channel audio. It builds on MiDashengLM-7B and adds a Spatial-Dasheng encoder. The model card says mono input still runs but carries no directional information.
Xiaomi says it will gradually roll out the model in smart home and car cockpit products, but has not given a timeline.
Written by AI from the articles below · updated Oct 15, 11:41 PM ET
Check the sources:
Article timeline
The articles in this story. Times are ET.
- PandailyNewsXiaomi open-sources MiDashengLM-Spatial audio model that locates sound sources
AIXiaomi has open-sourced MiDashengLM-Spatial, an roughly 8-billion-parameter audio model under Apache 2.0 that describes sounds and reasons about their direction, distance and movement from binaural input. The model builds on MiDashengLM-7B and adds a Spatial-Dasheng encoder, while mono input runs without directional information. Xiaomi says it will roll out the model gradually in smart home and car cockpit products, with no timeline given.
Heat trend
Not enough continuous observations to show a trend yet.