If you’re training to be a concert violinist, you don’t want your technique to be merely “good enough.” A new computer system may soon be able to help, as it uses artificial intelligence (AI) to identify a user’s bow technique, and could perhaps even tell them how to improve their performance.
Created by scientists at Spain’s Pompeu Fabra University, the system was trained using a gesture-recognizing Myo armband to track the right-arm movements of a professional violinist as she utilized the Détaché, Martelé, Spiccato, Ricochet, Sautillé, Staccato and Bariolage bow techniques. Audio of the performances was recorded at the same time.
Machine learning-based algorithms then compared the arm movements to the corresponding audio, determining which movements created which sounds, within each technique. When the system was subsequently tasked with identifying the technique that a violinist was using, it could do so with an accuracy of over 94 percent.
It is now hoped that once developed further, the technology could be used to provide students with real-time feedback, showing them where their form deviates from that of the pros.