Multi-Channel Automatic Music Transcription Using Tensor Algebra
This work addresses the challenge of automatic music transcription for polyphonic audio, which is important for music analysis and digitization, but appears incremental as it extends prior methods.
The paper tackles the problem of transcribing polyphonic music (chords) by introducing multi-channel automatic music transcription using tensor algebra, building on existing matrix factorization techniques to address the superposition of notes.
Music is an art, perceived in unique ways by every listener, coming from acoustic signals. In the meantime, standards as musical scores exist to describe it. Even if humans can make this transcription, it is costly in terms of time and efforts, even more with the explosion of information consecutively to the rise of the Internet. In that sense, researches are driven in the direction of Automatic Music Transcription. While this task is considered solved in the case of single notes, it is still open when notes superpose themselves, forming chords. This report aims at developing some of the existing techniques towards Music Transcription, particularly matrix factorization, and introducing the concept of multi-channel automatic music transcription. This concept will be explored with mathematical objects called tensors.