A pinboard by
Marius Miron

PhD candidate, Pompeu Fabra University, Barcelona


Think of it as karaoke for classical music instruments.

Music Information Retrieval is an interdisciplinary field at the crossroad between computer science and musicology. In particular, I am interested in applications which transform the way classical music is enjoyed. Being able to separate the audio corresponding to the instruments, allowed for interesting applications such as focusing on a particular sections in the orchestra or the re-creating the experience of the concert in virtual reality.

My research concerns audio signal processing and artificial intelligence. Traditionally, music source separation is done through a popular convex optimization technique, namely non-negative matrix factorization or, more recently, through deep learning. These approaches improve if we have the multi-microphone recordings of the piece, if we know which instruments are present in the piece, and if we have the score e.g. the notes played by each instrument. In fact, the more information we have about a music piece, the more we can restrict our model, and the better the resulting separation. For orchestral music the instruments are known, so we train timbre models for each instrument. Because any orchestral piece is accompanied by a score, we use the score information to further improve the separation.