Summary
MiDashengLM-Gen is an end-to-end framework for unified audio scene generation. Given a structured text description, it can generate a coherent scene that blends speech, music, sound effects, and environmental acoustics.
MiDashengLM-Gen is an end-to-end framework for unified audio scene generation. Given a structured text description, it can generate a coherent scene that blends speech, music, sound effects, and environmental acoustics.
The system combines a pretrained large language model and audio tokenizer with per-token conditional flow matching. It generates variable-length 16 kHz audio autoregressively using 768-dimensional semantic-acoustic latents at 25 Hz and a learned stop head.
Audio-text alignment pretraining maps audio latents into the language model token space before generation training. The result is a research system aimed at multimodal sound design, interactive environments, synthetic data, and multilingual expressive audio generation.
Get more likes & reach the top of search results by adding this button on your site!


Get top updates in AI to your inbox every weekend. It's free!