Unsupervised Transcription of Piano Music
Taylor Berg-Kirkpatrick · Jacob Andreas · Dan Klein

Wed Dec 10th 07:00 -- 11:59 PM @ Level 2, room 210D #None

We present a new probabilistic model for transcribing piano music from audio to a symbolic form. Our model reflects the process by which discrete musical events give rise to acoustic signals that are then superimposed to produce the observed data. As a result, the inference procedure for our model naturally resolves the source separation problem introduced by the the piano's polyphony. In order to adapt to the properties of a new instrument or acoustic environment being transcribed, we learn recording specific spectral profiles and temporal envelopes in an unsupervised fashion. Our system outperforms the best published approaches on a standard piano transcription task, achieving a 10.6% relative gain in note onset F1 on real piano audio.

Author Information

Taylor Berg-Kirkpatrick (UC Berkeley)
Jacob Andreas (UC Berkeley)
Dan Klein (UC Berkeley)

More from the Same Authors