3 results about "Music visualization" patented technology

The application discloses a music visualization method and device, a computer readable storage medium and a vehicle, wherein the method comprises: acquiring at least one frequency corresponding to an audio signal within a preset time before a current time; determining a frequency interval in which each frequency is located, and determining an amplitude corresponding to the frequency interval to obtain an amplitude corresponding to each frequency; wherein the frequency interval comprises a plurality of frequency intervals, each frequency interval has a corresponding amplitude; and controlling an atmosphere lamp according to each frequency and the amplitude corresponding to each frequency. Thus, the linkage between the atmosphere lamp and music can be realized, and different frequency characteristics of the vehicle-mounted music can be exhibited by controlling the atmosphere lamp, so that the visual presentation effect of the vehicle-mounted music is better, a more cool music atmosphere is created, and the user experience is improved.

This invention discloses a music-assisted image generation method based on music theory element extraction. The method specifically includes: extracting six-dimensional fine-grained structured music theory semantics from audio using a multimodal large language model and performing cross-modal consistency verification; constructing a neutral scene description based on the NSA (Neutral, Concise, White Space) principle to provide a semantic whiteboard; intelligently translating music theory elements into visual modification instructions using the large language model, adaptively rewriting the neutral scene to generate fusion prompts; and using the FastVAR model for efficient image generation. Compared with existing technologies, this invention effectively solves the problems of black-box feature extraction and semantic alignment ambiguity in audio-driven generation, eliminates logical conflicts caused by cross-modal splicing, and achieves high-quality generation while ensuring high-fidelity image texture details and semantic consistency. The method is intelligent and efficient, and has good application prospects in the fields of intelligent art creation and music visualization.