Transcription of polyphonic signals using fast filter bank

In this paper, a novel approach to the transcription of polyphonic signals is investigated. The method makes use of top-down analysis and bottom-up reconstruction of the time-frequency contents of the signals. Time-frequency contents of the signals are obtained using a bank of narrow band filters...

Full description

Saved in:
Bibliographic Details
Main Authors: Lee, Edwin Wei Thai, Foo, Say Wei
Other Authors: IEEE International Symposium on Circuits and Systems (2002 : Scottsdale, Arizona, US)
Format: Conference or Workshop Item
Language:English
Published: 2009
Online Access:https://hdl.handle.net/10356/90828
http://hdl.handle.net/10220/4616
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-90828
record_format dspace
spelling sg-ntu-dr.10356-908282019-12-06T17:54:45Z Transcription of polyphonic signals using fast filter bank Lee, Edwin Wei Thai Foo, Say Wei IEEE International Symposium on Circuits and Systems (2002 : Scottsdale, Arizona, US) In this paper, a novel approach to the transcription of polyphonic signals is investigated. The method makes use of top-down analysis and bottom-up reconstruction of the time-frequency contents of the signals. Time-frequency contents of the signals are obtained using a bank of narrow band filters with very sharp transition band. The filters are designed using the Frequency Response Masking technique. The high selectivity of the filters has enhanced the top-down analysis and increased the accuracy of identification over the simple frequency transform techniques. The method was tested with musical notes generated from an acoustic piano. Results show that for single notes and chords up to four notes, perfect identification can be achieved. Accepted version 2009-05-25T03:36:55Z 2019-12-06T17:54:45Z 2009-05-25T03:36:55Z 2019-12-06T17:54:45Z 2002 2002 Conference Paper Foo, S. W., & Lee, E. W. T. (2002). Transcription of polyphonic signals using fast filter bank. IEEE International Symposium on Circuits and Systems 2002. (pp. 241-244). https://hdl.handle.net/10356/90828 http://hdl.handle.net/10220/4616 en IEEE International Symposium on Circuits and Systems. Journal can be found at http://www.ieeexplore.ieee.org/xpl/RecentCon.jsp?punumber=7897 4 p. application/pdf
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
description In this paper, a novel approach to the transcription of polyphonic signals is investigated. The method makes use of top-down analysis and bottom-up reconstruction of the time-frequency contents of the signals. Time-frequency contents of the signals are obtained using a bank of narrow band filters with very sharp transition band. The filters are designed using the Frequency Response Masking technique. The high selectivity of the filters has enhanced the top-down analysis and increased the accuracy of identification over the simple frequency transform techniques. The method was tested with musical notes generated from an acoustic piano. Results show that for single notes and chords up to four notes, perfect identification can be achieved.
author2 IEEE International Symposium on Circuits and Systems (2002 : Scottsdale, Arizona, US)
author_facet IEEE International Symposium on Circuits and Systems (2002 : Scottsdale, Arizona, US)
Lee, Edwin Wei Thai
Foo, Say Wei
format Conference or Workshop Item
author Lee, Edwin Wei Thai
Foo, Say Wei
spellingShingle Lee, Edwin Wei Thai
Foo, Say Wei
Transcription of polyphonic signals using fast filter bank
author_sort Lee, Edwin Wei Thai
title Transcription of polyphonic signals using fast filter bank
title_short Transcription of polyphonic signals using fast filter bank
title_full Transcription of polyphonic signals using fast filter bank
title_fullStr Transcription of polyphonic signals using fast filter bank
title_full_unstemmed Transcription of polyphonic signals using fast filter bank
title_sort transcription of polyphonic signals using fast filter bank
publishDate 2009
url https://hdl.handle.net/10356/90828
http://hdl.handle.net/10220/4616
_version_ 1681034608435527680