High accuracy and octave error immune pitch detection algorithms

The aim of this paper is to present a method improving pitch estimation accuracy, showing high performance for both synthetic harmonic signals and musical instrument sounds. This method employs an Artificial Neural Network of a feed-forward type. In addition, octave error optimized pi...

Full description

Saved in:
Bibliographic Details
Main Authors: M. Dziubiński, B. Kostek
Format: Article
Language:English
Published: Institute of Fundamental Technological Research Polish Academy of Sciences 2004-01-01
Series:Archives of Acoustics
Online Access:https://acoustics.ippt.pan.pl/index.php/aa/article/view/464
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850105102892793856
author M. Dziubiński
B. Kostek
author_facet M. Dziubiński
B. Kostek
author_sort M. Dziubiński
collection DOAJ
description The aim of this paper is to present a method improving pitch estimation accuracy, showing high performance for both synthetic harmonic signals and musical instrument sounds. This method employs an Artificial Neural Network of a feed-forward type. In addition, octave error optimized pitch detection algorithm, based on spectral analysis is introduced. The proposed algorithm is very effective for signals with strong harmonic, as well as nearly sinusoidal contents. Experiments were performed on a variety of musical instrument sounds and sample results exemplifying main issues of both engineered algorithms are shown.
format Article
id doaj-art-fa56a3f1f0d34f88bd8076d98fb37d26
institution DOAJ
issn 0137-5075
2300-262X
language English
publishDate 2004-01-01
publisher Institute of Fundamental Technological Research Polish Academy of Sciences
record_format Article
series Archives of Acoustics
spelling doaj-art-fa56a3f1f0d34f88bd8076d98fb37d262025-08-20T02:39:11ZengInstitute of Fundamental Technological Research Polish Academy of SciencesArchives of Acoustics0137-50752300-262X2004-01-01291High accuracy and octave error immune pitch detection algorithmsM. Dziubiński0B. Kostek1Multimedia Systems Department Gdańsk University of TechnologyMultimedia Systems Department Gdańsk University of TechnologyThe aim of this paper is to present a method improving pitch estimation accuracy, showing high performance for both synthetic harmonic signals and musical instrument sounds. This method employs an Artificial Neural Network of a feed-forward type. In addition, octave error optimized pitch detection algorithm, based on spectral analysis is introduced. The proposed algorithm is very effective for signals with strong harmonic, as well as nearly sinusoidal contents. Experiments were performed on a variety of musical instrument sounds and sample results exemplifying main issues of both engineered algorithms are shown. https://acoustics.ippt.pan.pl/index.php/aa/article/view/464
spellingShingle M. Dziubiński
B. Kostek
High accuracy and octave error immune pitch detection algorithms
Archives of Acoustics
title High accuracy and octave error immune pitch detection algorithms
title_full High accuracy and octave error immune pitch detection algorithms
title_fullStr High accuracy and octave error immune pitch detection algorithms
title_full_unstemmed High accuracy and octave error immune pitch detection algorithms
title_short High accuracy and octave error immune pitch detection algorithms
title_sort high accuracy and octave error immune pitch detection algorithms
url https://acoustics.ippt.pan.pl/index.php/aa/article/view/464
work_keys_str_mv AT mdziubinski highaccuracyandoctaveerrorimmunepitchdetectionalgorithms
AT bkostek highaccuracyandoctaveerrorimmunepitchdetectionalgorithms