JERUSALEM, Nov. 10 (Xinhua) -- Israeli researchers used artificial intelligence (AI) to generate musically appealing personalized jazz solos that match human-specific preferences, Israeli Institute of Technology (Technion) said on Tuesday.
Thus, the computer science researchers showed that it is possible to model and optimize personalized jazz preference.
The team introduced a pipeline consisting of several steps: supervised learning using a corpus of original jazz solos, high-resolution user preference metric learning, and optimized generation of solos.
The corpus consisted of hundreds of solos performed by saxophone giants including Charlie Parker, Stan Getz, Sonny Stitt, and Dexter Gordon.
A plagiarism analysis was also performed to ensure that the generated solos are genuine rather than a concatenation of phrases previously seen in the corpus.
"Our work emphasizes the need to develop effective techniques to extract and distill noisy human feedback that will be required for effective quality evaluation of personalized AI art. Such techniques are a key to developing many cool applications," the researchers concluded.
Did you find this article insightful?