Multi-Pitch Estimation of Audio Recordings Using a Codebook-Based Approach

Martin Weiss Hansen; Jesper Rindom Jensen; Mads Græsbøll Christensen

doi:10.1109/EUSIPCO.2016.7760395

Multi-Pitch Estimation of Audio Recordings Using a Codebook-Based Approach

Martin Weiss Hansen, Jesper Rindom Jensen, Mads Græsbøll Christensen

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

2 Citations (Scopus)

374 Downloads (Pure)

Abstract

In this paper, a method for multi-pitch estimation of single-channel mixtures of harmonic signals is presented. Using the method, it is possible to resolve amplitudes of overlapping harmonics, which is otherwise an ill-posed problem. The method is based on the extended invariance principle (EXIP), and a codebook consisting of realistic amplitude vectors. A nonlinear least squares (NLS) cost function is formed based on the observed signal and a parametric model of the signal, for a set of fundamental frequency candidates. For each of these, amplitude estimates are computed. The magnitudes of these estimates are quantized according to a codebook, and an updated cost function is used to estimate the fundamental frequencies of the sources. The performance of the proposed estimator is evaluated using synthetic and real mixtures, and the results show that the proposed method is able to estimate multiple pitches in a mixture of sources with overlapping harmonics.

Original language	English
Title of host publication	Proceedings of the 24th European Signal Processing Conference (EUSIPCO)
Publisher	IEEE
Publication date	2016
Pages	983-987
ISBN (Print)	978-0-9928-6265-7
DOIs	https://doi.org/10.1109/EUSIPCO.2016.7760395
Publication status	Published - 2016
Event	24th European Signal Processing Conference - Hilton Budapest, Budapest, Hungary Duration: 29 Aug 2016 → 2 Sept 2016 Conference number: 24

Conference

Conference	24th European Signal Processing Conference
Number	24
Location	Hilton Budapest
Country/Territory	Hungary
City	Budapest
Period	29/08/2016 → 02/09/2016

Series	Proceedings of the European Signal Processing Conference (EUSIPCO)
ISSN	2076-1465

Keywords

multi-pitch estimation
amplitude estimation
vector quantization
music information retrieval

Access to Document

10.1109/EUSIPCO.2016.7760395

EUSIPCO2016_mwhAccepted author manuscript, 1.02 MB

AUB Link

Search for the material in Aalborg University Library's search engine

Localization and Tracking of Speech - a Joint Audio-Visual Approach
Jensen, J. R.
01/10/2013 → 30/09/2016
Project: Research
Spatio-Temporal Filtering Methods for Enhancement and Separation of Speech Signals
Christensen, M. G., Nørholm, S. M., Karimian-Azari, S. & Jensen, J. R.
01/08/2012 → 30/06/2015
Project: Research

Cite this

@inproceedings{806d34eeaeb242b8a5a01c0e0c977184,

title = "Multi-Pitch Estimation of Audio Recordings Using a Codebook-Based Approach",

abstract = "In this paper, a method for multi-pitch estimation of single-channel mixtures of harmonic signals is presented. Using the method, it is possible to resolve amplitudes of overlapping harmonics, which is otherwise an ill-posed problem. The method is based on the extended invariance principle (EXIP), and a codebook consisting of realistic amplitude vectors. A nonlinear least squares (NLS) cost function is formed based on the observed signal and a parametric model of the signal, for a set of fundamental frequency candidates. For each of these, amplitude estimates are computed. The magnitudes of these estimates are quantized according to a codebook, and an updated cost function is used to estimate the fundamental frequencies of the sources. The performance of the proposed estimator is evaluated using synthetic and real mixtures, and the results show that the proposed method is able to estimate multiple pitches in a mixture of sources with overlapping harmonics.",

keywords = "multi-pitch estimation, amplitude estimation, vector quantization, music information retrieval",

author = "Hansen, {Martin Weiss} and Jensen, {Jesper Rindom} and Christensen, {Mads Gr{\ae}sb{\o}ll}",

year = "2016",

doi = "10.1109/EUSIPCO.2016.7760395",

language = "English",

isbn = "978-0-9928-6265-7",

series = "Proceedings of the European Signal Processing Conference (EUSIPCO)",

publisher = "IEEE",

pages = "983--987",

booktitle = "Proceedings of the 24th European Signal Processing Conference (EUSIPCO)",

address = "United States",

note = "24th European Signal Processing Conference, EUSIPCO 2016 ; Conference date: 29-08-2016 Through 02-09-2016",

}

Hansen, MW, Jensen, JR & Christensen, MG 2016, Multi-Pitch Estimation of Audio Recordings Using a Codebook-Based Approach. in Proceedings of the 24th European Signal Processing Conference (EUSIPCO). IEEE, Proceedings of the European Signal Processing Conference (EUSIPCO), pp. 983-987, 24th European Signal Processing Conference, Budapest, Hungary, 29/08/2016. https://doi.org/10.1109/EUSIPCO.2016.7760395

Multi-Pitch Estimation of Audio Recordings Using a Codebook-Based Approach. / Hansen, Martin Weiss; Jensen, Jesper Rindom ; Christensen, Mads Græsbøll.
Proceedings of the 24th European Signal Processing Conference (EUSIPCO). IEEE, 2016. p. 983-987 (Proceedings of the European Signal Processing Conference (EUSIPCO)).

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

TY - GEN

T1 - Multi-Pitch Estimation of Audio Recordings Using a Codebook-Based Approach

AU - Hansen, Martin Weiss

AU - Jensen, Jesper Rindom

AU - Christensen, Mads Græsbøll

N1 - Conference code: 24

PY - 2016

Y1 - 2016

N2 - In this paper, a method for multi-pitch estimation of single-channel mixtures of harmonic signals is presented. Using the method, it is possible to resolve amplitudes of overlapping harmonics, which is otherwise an ill-posed problem. The method is based on the extended invariance principle (EXIP), and a codebook consisting of realistic amplitude vectors. A nonlinear least squares (NLS) cost function is formed based on the observed signal and a parametric model of the signal, for a set of fundamental frequency candidates. For each of these, amplitude estimates are computed. The magnitudes of these estimates are quantized according to a codebook, and an updated cost function is used to estimate the fundamental frequencies of the sources. The performance of the proposed estimator is evaluated using synthetic and real mixtures, and the results show that the proposed method is able to estimate multiple pitches in a mixture of sources with overlapping harmonics.

AB - In this paper, a method for multi-pitch estimation of single-channel mixtures of harmonic signals is presented. Using the method, it is possible to resolve amplitudes of overlapping harmonics, which is otherwise an ill-posed problem. The method is based on the extended invariance principle (EXIP), and a codebook consisting of realistic amplitude vectors. A nonlinear least squares (NLS) cost function is formed based on the observed signal and a parametric model of the signal, for a set of fundamental frequency candidates. For each of these, amplitude estimates are computed. The magnitudes of these estimates are quantized according to a codebook, and an updated cost function is used to estimate the fundamental frequencies of the sources. The performance of the proposed estimator is evaluated using synthetic and real mixtures, and the results show that the proposed method is able to estimate multiple pitches in a mixture of sources with overlapping harmonics.

KW - multi-pitch estimation

KW - amplitude estimation

KW - vector quantization

KW - music information retrieval

U2 - 10.1109/EUSIPCO.2016.7760395

DO - 10.1109/EUSIPCO.2016.7760395

M3 - Article in proceeding

SN - 978-0-9928-6265-7

T3 - Proceedings of the European Signal Processing Conference (EUSIPCO)

SP - 983

EP - 987

BT - Proceedings of the 24th European Signal Processing Conference (EUSIPCO)

PB - IEEE

T2 - 24th European Signal Processing Conference

Y2 - 29 August 2016 through 2 September 2016

ER -

Multi-Pitch Estimation of Audio Recordings Using a Codebook-Based Approach

Abstract

Conference

Keywords

Access to Document

AUB Link

Fingerprint

Projects

Localization and Tracking of Speech - a Joint Audio-Visual Approach

Spatio-Temporal Filtering Methods for Enhancement and Separation of Speech Signals

Cite this