In playing music, gestures are extremely important, to some degree since they are straightforwardly identified with the sound and the expressiveness of the musicians. Today, technology exists that catches movement and is equipped for recognizing gestural subtleties in all respects absolutely. In an investigation distributed for the last month of March in Frontiers in Psychology, David Dalmazzo and Rafael Ramírez, individuals from the Music and Machine Learning Lab of the Music Technology Group (MTG) at the Department of Information and Communication Technologies (DTIC) of UPF, apply artificial intelligence to the automatic classification of violin bow gestures as indicated by the performer’s movement.
“We recorded movement and audio data corresponding to seven representative bow techniques (Détaché, Martelé, Spiccato, Ricochet, Sautillé, Staccato and Bariolage) performed by a professional violinist. We obtained information about the inertial motion from the right forearm and we synchronized it with the audio recordings,” clarify Dalmazzo and Ramírez, creators of the examination.
A framework recognizes violinists’ bowing procedures with 94% exactness
The information utilized in this investigation are accessible in an online public repository. In the wake of extracting the characteristics of the data concerning movement and audio, the scientists trained a framework to automatically distinguish the different bow systems utilized in playing the violin. The model can decide the distinctive methods concentrated to over 94% precision. The outcomes empower applying this work to a practical learning scenario, in which students of violin can profit by the feedback given by the framework in real time.
This examination was led inside the structure of the TELMI (Technology Enhanced Learning Performance of Musical Instrument) project. Its motivation is to research how technology (sensors, multimodal information, Artificial intelligence, and PC frameworks) can improve the practices of students of music, helping them to concentrate on the exact advancement of good practices, particularly while incorporating new musical skills.
With the violin as a case study, one of the main objectives of the project is to provide students with feedback in real time, just as enabling them to contrast their performances and those of leading specialists. “Our findings have already been generalized to other musical instruments and applied in music education environments,” includes Rafael Ramírez, principal investigator of the project.