A Discriminative Model for Polyphonic Piano Transcription

A Discriminative Model for Polyphonic Piano Transcription

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 s...

Full description

Bibliographic Details
Main Authors: Daniel P. W. Ellis, Graham E. Poliner
Format: Article
Language:English
Published: SpringerOpen 2007-01-01
Series:EURASIP Journal on Advances in Signal Processing
Online Access:http://dx.doi.org/10.1155/2007/48317
id doaj-74da3f5a7f21402a8c45a640d1da62d5
record_format Article
spelling doaj-74da3f5a7f21402a8c45a640d1da62d52020-11-24T21:07:12ZengSpringerOpenEURASIP Journal on Advances in Signal Processing1687-61721687-61802007-01-01200710.1155/2007/48317A Discriminative Model for Polyphonic Piano TranscriptionDaniel P. W. EllisGraham E. PolinerWe 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. http://dx.doi.org/10.1155/2007/48317
collection DOAJ
language English
format Article
sources DOAJ
author Daniel P. W. Ellis
Graham E. Poliner
spellingShingle Daniel P. W. Ellis
Graham E. Poliner
A Discriminative Model for Polyphonic Piano Transcription
EURASIP Journal on Advances in Signal Processing
author_facet Daniel P. W. Ellis
Graham E. Poliner
author_sort Daniel P. W. Ellis
title A Discriminative Model for Polyphonic Piano Transcription
title_short A Discriminative Model for Polyphonic Piano Transcription
title_full A Discriminative Model for Polyphonic Piano Transcription
title_fullStr A Discriminative Model for Polyphonic Piano Transcription
title_full_unstemmed A Discriminative Model for Polyphonic Piano Transcription
title_sort discriminative model for polyphonic piano transcription
publisher SpringerOpen
series EURASIP Journal on Advances in Signal Processing
issn 1687-6172
1687-6180
publishDate 2007-01-01
description 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.
url http://dx.doi.org/10.1155/2007/48317
work_keys_str_mv AT danielpwellis adiscriminativemodelforpolyphonicpianotranscription
AT grahamepoliner adiscriminativemodelforpolyphonicpianotranscription
AT danielpwellis discriminativemodelforpolyphonicpianotranscription
AT grahamepoliner discriminativemodelforpolyphonicpianotranscription
_version_ 1716763720773795840

Similar Items