In the project Musical AI (Call: Proyectos de I+D+i - PGC 2019; project no. PID2019-111403GB-I00)  we will work on a number of research topics related to large-scale corpora and data-driven machine learning, with applications to music applications. We plan to increase our understanding of music, developing AI-based models and tools for helping listeners to gain musical understanding and appreciation, and developing AI-based models for helping music learning and music creation.

The project NextCore (Call: Retos-Colaboración 2019 del Ministerio de Ciencia e Innovación; project no. RTC2019-007248-7) is coordinated by our spin-off Company BMAT and in it the MTG will work on developing technologies to improve the current state of the art in automatic music monitoring. In particular the goal is to work on deep learning architectures specific for this problem, being able to improve the music detection by pre-processing the captured audio signals in situations like when the music is in the background or when the recording is of low quality, and to investigate new architectures for scalable music cover detection.