AI & ML interests
Building industrial-grade audio data infrastructure for Large Audio Models (LAM). Specializing in 192kHz/32-bit physical ground-truth acoustics, 100% anechoic capture (RT60 < 0.2s), zero-crosstalk multitrack separation, and 7.1.4 Dolby Atmos stemming for Generative AI training.
Recent Activity
sonicsets-data 's models
None public yet