Researchers from Spain have developed a way to apply artificial intelligence to the automatic classification of violin bow gestures according to the performer's movement.
For many instruments, a musician's gestures are essential as they relate directly to the sound produced by the instrument and to the expressiveness of the music being played.
RELATED: 3 START-UPS LEADING THE MUSICAL AI REVOLUTION
This is particularly true of violin where the musician's arm movements are critical for producing the right sound. There has been much work done to create technology capable of detecting gestural details very precisely.
System can quickly recognize good gestures
David Dalmazzo and Rafael Ramírez, members of the Music and Machine Learning Lab of the Music Technology Group (MTG) at the Department of Information and Communication Technologies (DTIC) of UPF have taken this technology further and created a way for artificial intelligence to classify bow movements with 94% accuracy.
"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", explain Dalmazzo and Ramírez, authors of the study. The two researchers used data that was publicly available.
Students learn via AI
They extracted the information from the data related to movement and audio; they trained an algorithm to identify the different bow techniques used in playing the violin. With such a high accuracy rate the system will become an important learning tool for students who can benefit from the feedback provided by the system in real time.
The researchers were working as part of the TELMI (Technology Enhanced Learning Performance of Musical Instrument) project which aims to investigate how technology (sensors, multimodal data, artificial intelligence, and computer systems) can improve the practices of students of music.
Budding musicians are given a hand
The project aims to find ways to help students focus on the precise development of good practices. With the violin project, the aim was to create a tool that provides students with feedback in real time.
RELATED: MEET ENDEL: THE FIRST-EVER ALGORITHM TO SIGN A MUSIC DISTRIBUTION DEAL WITH A MAJOR LABEL
The project also aimed at giving the students a clear way of comparing their performances with those of leading experts.
"Our findings have already been generalized to other musical instruments and applied in music education environments," adds Rafael Ramírez, principal investigator of the project.
Technology influences music production
Technology has been shaping the way students learn and practice music for centuries.
For example way back in 1877, the phonograph brought music into the homes of people who may have otherwise been rarely able to afford a concert ticket. Being able to listen to music from all over the world at home must have inspired generations of people to pick up an instrument.
As music has become more accessible even the most unexpected of people can record and release tracks that can be listened to anyone all over the world. Mr. Musk is that you?