Home

A Discriminative Model for Polyphonic Piano Transcription

Graham E. Poliner; Daniel P. W. Ellis

Title:
A Discriminative Model for Polyphonic Piano Transcription
Author(s):
Poliner, Graham E.
Ellis, Daniel P. W.
Date:
Type:
Articles
Department:
Electrical Engineering
Volume:
2007
Permanent URL:
Book/Journal Title:
EURASIP Journal on Advances in Signal Processing
Abstract:
We present a discriminative model for polyphonic piano transcription. Support vector machines trained on spectral features are used to classify frame-level note instances. The classifier outputs are temporally constrained via hidden Markov models, and the proposed system is used to transcribe both synthesized and real piano recordings. A frame-level transcription accuracy of 68% was achieved on a newly generated test set, and direct comparisons to previous approaches are provided.
Subject(s):
Artificial intelligence
Music
Publisher DOI:
10.1155/2007
Item views:
62
Metadata:
text | xml

In Partnership with the Center for Digital Research and Scholarship at Columbia University Libraries/Information Services | Terms of Use