Abstract | ||
---|---|---|
In this paper we improve piano note tracking using a Hidden Markov Model (HMM). We first transcribe piano music based on a non-negative matrix factorisation (NMF) method. For each note four templates are trained to represent the different stages of piano sounds: silence, attack, decay and release. Then a four-state HMM is employed to track notes on the gains of each pitch. We increase the likelihood of staying in silence for low pitches and set a minimum duration to reduce short false-positive notes. For quickly repeated notes, we allow the note state to transition from decay directly back to attack. The experiments tested on 30 piano pieces from the MAPS dataset shows promising results for both frame-wise and note-wise transcription. |
Year | Venue | Keywords |
---|---|---|
2015 | European Signal Processing Conference | piano note tracking,Hidden Markov Model |
Field | DocType | ISSN |
Markov model,Computer science,Spectrogram,Matrix decomposition,Speech recognition,Smoothing,Non-negative matrix factorization,Piano,Hidden Markov model,Silence | Conference | 2076-1465 |
Citations | PageRank | References |
2 | 0.40 | 14 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Tian Cheng | 1 | 20 | 4.89 |
Simon Dixon | 2 | 1164 | 107.57 |
Matthias Mauch | 3 | 381 | 26.97 |