A query-by-humming music information retrieval from audio signals based on multiple F0 candidates

Akinori Ito; Yu Kosugi; Shozo Makino; Masashi Ito

doi:10.1109/ICALIP.2010.5685029

A query-by-humming music information retrieval from audio signals based on multiple F0 candidates

Akinori Ito, Yu Kosugi, Shozo Makino, Masashi Ito

ENG - Communications Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

In this paper, we propose a query-by-humming (QbH) system that retrieves musical pieces given as audio signals. Most conventional QbH systems assume that the symbolic melody information is given a priori, which is not always true. In our system, the database for retrieval is generated from 1ch audio signal that contains many sounds. We generate the database by estimating fundamental frequencies (F0) of the audio signals frame by frame. To improve the retrieval accuracy, we exploit multiple F0 candidates to absorb the impact of F0 estimation errors. From the experiment, we obtained about 15 points of improvement by using multiple F0 candidates, compared with the QbH system with only one F0 candidate .

Original language	English
Title of host publication	ICALIP 2010 - 2010 International Conference on Audio, Language and Image Processing, Proceedings
Pages	1-5
Number of pages	5
DOIs	https://doi.org/10.1109/ICALIP.2010.5685029
Publication status	Published - 2010 Dec 1
Event	2010 International Conference on Audio, Language and Image Processing, ICALIP 2010 - Shanghai, China Duration: 2010 Nov 23 → 2010 Nov 25

Publication series

Name	ICALIP 2010 - 2010 International Conference on Audio, Language and Image Processing, Proceedings

Other

Other	2010 International Conference on Audio, Language and Image Processing, ICALIP 2010
Country/Territory	China
City	Shanghai
Period	10/11/23 → 10/11/25

ASJC Scopus subject areas

Language and Linguistics
Computer Vision and Pattern Recognition
Linguistics and Language

Access to Document

10.1109/ICALIP.2010.5685029

Cite this

Ito, A., Kosugi, Y., Makino, S., & Ito, M. (2010). A query-by-humming music information retrieval from audio signals based on multiple F0 candidates. In ICALIP 2010 - 2010 International Conference on Audio, Language and Image Processing, Proceedings (pp. 1-5). [5685029] (ICALIP 2010 - 2010 International Conference on Audio, Language and Image Processing, Proceedings). https://doi.org/10.1109/ICALIP.2010.5685029

A query-by-humming music information retrieval from audio signals based on multiple F0 candidates. / Ito, Akinori; Kosugi, Yu; Makino, Shozo et al.
ICALIP 2010 - 2010 International Conference on Audio, Language and Image Processing, Proceedings. 2010. p. 1-5 5685029 (ICALIP 2010 - 2010 International Conference on Audio, Language and Image Processing, Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Ito, A, Kosugi, Y, Makino, S & Ito, M 2010, A query-by-humming music information retrieval from audio signals based on multiple F0 candidates. in ICALIP 2010 - 2010 International Conference on Audio, Language and Image Processing, Proceedings., 5685029, ICALIP 2010 - 2010 International Conference on Audio, Language and Image Processing, Proceedings, pp. 1-5, 2010 International Conference on Audio, Language and Image Processing, ICALIP 2010, Shanghai, China, 10/11/23. https://doi.org/10.1109/ICALIP.2010.5685029

Ito A, Kosugi Y, Makino S, Ito M. A query-by-humming music information retrieval from audio signals based on multiple F0 candidates. In ICALIP 2010 - 2010 International Conference on Audio, Language and Image Processing, Proceedings. 2010. p. 1-5. 5685029. (ICALIP 2010 - 2010 International Conference on Audio, Language and Image Processing, Proceedings). doi: 10.1109/ICALIP.2010.5685029

@inproceedings{7d595b99f59745d5a12526697e882384,

title = "A query-by-humming music information retrieval from audio signals based on multiple F0 candidates",

abstract = "In this paper, we propose a query-by-humming (QbH) system that retrieves musical pieces given as audio signals. Most conventional QbH systems assume that the symbolic melody information is given a priori, which is not always true. In our system, the database for retrieval is generated from 1ch audio signal that contains many sounds. We generate the database by estimating fundamental frequencies (F0) of the audio signals frame by frame. To improve the retrieval accuracy, we exploit multiple F0 candidates to absorb the impact of F0 estimation errors. From the experiment, we obtained about 15 points of improvement by using multiple F0 candidates, compared with the QbH system with only one F0 candidate .",

author = "Akinori Ito and Yu Kosugi and Shozo Makino and Masashi Ito",

year = "2010",

month = dec,

day = "1",

doi = "10.1109/ICALIP.2010.5685029",

language = "English",

isbn = "9781424458653",

series = "ICALIP 2010 - 2010 International Conference on Audio, Language and Image Processing, Proceedings",

pages = "1--5",

booktitle = "ICALIP 2010 - 2010 International Conference on Audio, Language and Image Processing, Proceedings",

note = "2010 International Conference on Audio, Language and Image Processing, ICALIP 2010 ; Conference date: 23-11-2010 Through 25-11-2010",

}

TY - GEN

T1 - A query-by-humming music information retrieval from audio signals based on multiple F0 candidates

AU - Ito, Akinori

AU - Kosugi, Yu

AU - Makino, Shozo

AU - Ito, Masashi

PY - 2010/12/1

Y1 - 2010/12/1

N2 - In this paper, we propose a query-by-humming (QbH) system that retrieves musical pieces given as audio signals. Most conventional QbH systems assume that the symbolic melody information is given a priori, which is not always true. In our system, the database for retrieval is generated from 1ch audio signal that contains many sounds. We generate the database by estimating fundamental frequencies (F0) of the audio signals frame by frame. To improve the retrieval accuracy, we exploit multiple F0 candidates to absorb the impact of F0 estimation errors. From the experiment, we obtained about 15 points of improvement by using multiple F0 candidates, compared with the QbH system with only one F0 candidate .

AB - In this paper, we propose a query-by-humming (QbH) system that retrieves musical pieces given as audio signals. Most conventional QbH systems assume that the symbolic melody information is given a priori, which is not always true. In our system, the database for retrieval is generated from 1ch audio signal that contains many sounds. We generate the database by estimating fundamental frequencies (F0) of the audio signals frame by frame. To improve the retrieval accuracy, we exploit multiple F0 candidates to absorb the impact of F0 estimation errors. From the experiment, we obtained about 15 points of improvement by using multiple F0 candidates, compared with the QbH system with only one F0 candidate .

UR - http://www.scopus.com/inward/record.url?scp=79851489270&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79851489270&partnerID=8YFLogxK

U2 - 10.1109/ICALIP.2010.5685029

DO - 10.1109/ICALIP.2010.5685029

M3 - Conference contribution

AN - SCOPUS:79851489270

SN - 9781424458653

T3 - ICALIP 2010 - 2010 International Conference on Audio, Language and Image Processing, Proceedings

SP - 1

EP - 5

BT - ICALIP 2010 - 2010 International Conference on Audio, Language and Image Processing, Proceedings

T2 - 2010 International Conference on Audio, Language and Image Processing, ICALIP 2010

Y2 - 23 November 2010 through 25 November 2010

ER -

A query-by-humming music information retrieval from audio signals based on multiple F0 candidates

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this