Automatic music transcription: from monophonic to polyphonic

Music understanding from audio track and performance is a key problem and a challenge for many applications ranging from: automated music transcoding, music education, interactive performance, etc. The transcoding of polyphonic music is a one of the most complex and still open task to be solved in order to become a common tool for the above mentioned applications. Techniques suitable for monophonic transcoding have shown to be largely unsuitable for polyphonic cases. Recently, a range of polyphonic understanding algorithms and models have been proposed and compared against worldwide accepted test cases such as those adopted in the MIREX competition. Several different approaches are based on techniques such as: nonnegative matrix factorization, pitch trajectory analysis, harmonic clustering, bispectral analysis, event tracking, nonnegative matrix factorization, hidden Markov model. This chapter analyzes the evolution of music understanding algorithms and models from monophonic to polyphonic, showing and comparing the solutions, while analysing them against commonly accepted assessment methods and formal metrics.