While questions regarding licensing for AI music haven't been settled, a 2021 whitepaper from Eric Sunray (now working for the Music Publishers Association) suggested that there's enough "coherent" traces of the original sounds that AI music can violate reproduction rights. Roughly one percent of the music produced at the time of publication was copied directly from the training songs. As with other Google AI generators, the researchers aren't releasing MusicLM to the public over copyright concerns. Just don't plan on using the tech any time soon. Don't expect an EDM-style drop or the verse-chorus-verse pattern of a typical song. And while the performances themselves are better than you'd expect, they can be repetitive in ways human works might not. Some compositions sound strange, and vocals tend to be incomprehensible. MusicLM has its problems, as with many AI generators. A story mode can stitch several descriptions together to produce a DJ set or soundtrack. The technology can even craft melodies based on humming, whistling or the description of a painting. If you want a hybrid of dance music and reggaeton with a "spacey, otherworldly" tune that evokes a "sense of wonder and awe," MusicLM can make it happen. The AI can not only combine genres and instruments, but write tracks using abstract concepts that are normally difficult for computers to grasp. However, MusicLM's model and vast training database (280,000 hours of music) help it produce music with surprising variety and depth. As TechCrunch notes, projects like Google's AudioML and OpenAI's Jukebox have tackled the subject. Google recently published research on MusicLM, a system that creates music in any genre with a text description. Never mind ChatGPT - music might be the next big frontier for AI content generation.
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |