An innovative approach to transcription of polyphonic signals
In this paper, a new method is proposed to separate and identify polyphonic signals generated by an acoustic piano. The method consists of a top down extraction architecture using a harmonics-tracking algorithm followed by a bottom up reconstruction architecture based on a set of the expected profil...
Saved in:
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Conference or Workshop Item |
Language: | English |
Published: |
2009
|
Online Access: | https://hdl.handle.net/10356/90569 http://hdl.handle.net/10220/4613 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-90569 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-905692019-12-06T17:50:02Z An innovative approach to transcription of polyphonic signals Foo, Say Wei Lee, Edwin Wei Thai IEEE International Conference on Information, Communications and Signal Processing (3rd : 2001 : Singapore) In this paper, a new method is proposed to separate and identify polyphonic signals generated by an acoustic piano. The method consists of a top down extraction architecture using a harmonics-tracking algorithm followed by a bottom up reconstruction architecture based on a set of the expected profiles of single notes. In addition to the architectures mentioned above, a heuristic function is also included to further re-enforce the robustness and the ability to recognize multiple notes and to pull apart octave unison. The algorithm was tested with chords that consist of multiple notes. Some of the notes are one octave apart. It is shown that a recognition accuracy of 96% can be achieved using the proposed method. Accepted version 2009-05-25T01:16:24Z 2019-12-06T17:50:02Z 2009-05-25T01:16:24Z 2019-12-06T17:50:02Z 2001 2001 Conference Paper Lee, E., & Foo, S. W. (2001). An innovative approach to transcription of polyphonic signals. International Conference on Information, Communications & Signal Processing, 1-5. https://hdl.handle.net/10356/90569 http://hdl.handle.net/10220/4613 en © IEEE. http://ieeexplore.ieee.org/xpl/RecentCon.jsp?punumber=5224 5 p. application/pdf |
institution |
Nanyang Technological University |
building |
NTU Library |
country |
Singapore |
collection |
DR-NTU |
language |
English |
description |
In this paper, a new method is proposed to separate and identify polyphonic signals generated by an acoustic piano. The method consists of a top down extraction architecture using a harmonics-tracking algorithm followed by a bottom up reconstruction architecture based on a set of the expected profiles of single notes. In addition to the architectures mentioned above, a heuristic function is also included to further re-enforce the robustness and the ability to recognize multiple notes and to pull apart octave unison. The algorithm was tested with chords that consist of multiple notes. Some of the notes are one octave apart. It is shown that a recognition accuracy of 96% can be achieved using the proposed method. |
author2 |
IEEE International Conference on Information, Communications and Signal Processing (3rd : 2001 : Singapore) |
author_facet |
IEEE International Conference on Information, Communications and Signal Processing (3rd : 2001 : Singapore) Foo, Say Wei Lee, Edwin Wei Thai |
format |
Conference or Workshop Item |
author |
Foo, Say Wei Lee, Edwin Wei Thai |
spellingShingle |
Foo, Say Wei Lee, Edwin Wei Thai An innovative approach to transcription of polyphonic signals |
author_sort |
Foo, Say Wei |
title |
An innovative approach to transcription of polyphonic signals |
title_short |
An innovative approach to transcription of polyphonic signals |
title_full |
An innovative approach to transcription of polyphonic signals |
title_fullStr |
An innovative approach to transcription of polyphonic signals |
title_full_unstemmed |
An innovative approach to transcription of polyphonic signals |
title_sort |
innovative approach to transcription of polyphonic signals |
publishDate |
2009 |
url |
https://hdl.handle.net/10356/90569 http://hdl.handle.net/10220/4613 |
_version_ |
1681040975491760128 |