A robust singing melody tracker using adaptive round semitones (ARS)

Chong Kai Wang; Ren Yuan Lyu; Yuang Chin Chiang

doi:10.1109/ISPA.2003.1296957

A robust singing melody tracker using adaptive round semitones (ARS)

Chong Kai Wang
, Ren Yuan Lyu
, Yuang Chin Chiang

Department of Computer Science and Information Engineering

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

5 Scopus citations

Abstract

In this paper, an approach for melody tracking is proposed and applied to applications of automatic singing transcription. The melody tracker is based on adaptive round semitones (ARS) algorithm, which converts a pitch contour of singing voice to a sequence of music notes. The pitch of singing voice is usually much more unstable than that of musical instruments. A poor-skilled singer may generate voice with even worse pitch correctness. ARS deals with these issues by using a statistic model, which predicts singers' tune scale of the current note dynamically. Compared with the other approaches, ARS achieves the lowest error rate for poor singers and seems much more insensitive to the diversity of singers' singing skills. Furthermore, by adding on the transcription process a heuristic music grammar constraints based on music theory, the error rate can be reduced 20.5%, which beats all the other approaches mentioned in the other literatures.

Original language	English
Title of host publication	ISPA 2003 - Proceedings of the 3rd International Symposium on Image and Signal Processing and Analysis
Editors	A. Neri, H. Babic, S. Loncaric
Publisher	IEEE Computer Society
Pages	549-554
Number of pages	6
ISBN (Electronic)	953184061X
DOIs	https://doi.org/10.1109/ISPA.2003.1296957
State	Published - 2003
Event	3rd International Symposium on Image and Signal Processing and Analysis, ISPA 2003 - Rome, Italy Duration: 18 09 2003 → 20 09 2003

Publication series

Name	International Symposium on Image and Signal Processing and Analysis, ISPA
Volume	1
ISSN (Print)	1845-5921
ISSN (Electronic)	1849-2266

Conference

Conference	3rd International Symposium on Image and Signal Processing and Analysis, ISPA 2003
Country/Territory	Italy
City	Rome
Period	18/09/03 → 20/09/03

Bibliographical note

Publisher Copyright:
© 2003 IEEE.

Keywords

Algorithm design and analysis
Error analysis
Instruments
Multimedia databases
Multiple signal classification
Predictive models
Robustness
Signal processing algorithms
Software algorithms
Statistics

Access to Document

10.1109/ISPA.2003.1296957

Cite this

Wang, C. K., Lyu, R. Y., & Chiang, Y. C. (2003). A robust singing melody tracker using adaptive round semitones (ARS). In A. Neri, H. Babic, & S. Loncaric (Eds.), ISPA 2003 - Proceedings of the 3rd International Symposium on Image and Signal Processing and Analysis (pp. 549-554). Article 1296957 (International Symposium on Image and Signal Processing and Analysis, ISPA; Vol. 1). IEEE Computer Society. https://doi.org/10.1109/ISPA.2003.1296957

Wang, Chong Kai ; Lyu, Ren Yuan ; Chiang, Yuang Chin. / A robust singing melody tracker using adaptive round semitones (ARS). ISPA 2003 - Proceedings of the 3rd International Symposium on Image and Signal Processing and Analysis. editor / A. Neri ; H. Babic ; S. Loncaric. IEEE Computer Society, 2003. pp. 549-554 (International Symposium on Image and Signal Processing and Analysis, ISPA).

@inproceedings{c6150c4426a547c784d1408c952a56a0,

title = "A robust singing melody tracker using adaptive round semitones (ARS)",

abstract = "In this paper, an approach for melody tracking is proposed and applied to applications of automatic singing transcription. The melody tracker is based on adaptive round semitones (ARS) algorithm, which converts a pitch contour of singing voice to a sequence of music notes. The pitch of singing voice is usually much more unstable than that of musical instruments. A poor-skilled singer may generate voice with even worse pitch correctness. ARS deals with these issues by using a statistic model, which predicts singers' tune scale of the current note dynamically. Compared with the other approaches, ARS achieves the lowest error rate for poor singers and seems much more insensitive to the diversity of singers' singing skills. Furthermore, by adding on the transcription process a heuristic music grammar constraints based on music theory, the error rate can be reduced 20.5\%, which beats all the other approaches mentioned in the other literatures.",

keywords = "Algorithm design and analysis, Error analysis, Instruments, Multimedia databases, Multiple signal classification, Predictive models, Robustness, Signal processing algorithms, Software algorithms, Statistics",

author = "Wang, \{Chong Kai\} and Lyu, \{Ren Yuan\} and Chiang, \{Yuang Chin\}",

note = "Publisher Copyright: {\textcopyright} 2003 IEEE.; 3rd International Symposium on Image and Signal Processing and Analysis, ISPA 2003 ; Conference date: 18-09-2003 Through 20-09-2003",

year = "2003",

doi = "10.1109/ISPA.2003.1296957",

language = "英语",

series = "International Symposium on Image and Signal Processing and Analysis, ISPA",

publisher = "IEEE Computer Society",

pages = "549--554",

editor = "A. Neri and H. Babic and S. Loncaric",

booktitle = "ISPA 2003 - Proceedings of the 3rd International Symposium on Image and Signal Processing and Analysis",

address = "美国",

}

Wang, CK, Lyu, RY & Chiang, YC 2003, A robust singing melody tracker using adaptive round semitones (ARS). in A Neri, H Babic & S Loncaric (eds), ISPA 2003 - Proceedings of the 3rd International Symposium on Image and Signal Processing and Analysis., 1296957, International Symposium on Image and Signal Processing and Analysis, ISPA, vol. 1, IEEE Computer Society, pp. 549-554, 3rd International Symposium on Image and Signal Processing and Analysis, ISPA 2003, Rome, Italy, 18/09/03. https://doi.org/10.1109/ISPA.2003.1296957

A robust singing melody tracker using adaptive round semitones (ARS). / Wang, Chong Kai; Lyu, Ren Yuan; Chiang, Yuang Chin.
ISPA 2003 - Proceedings of the 3rd International Symposium on Image and Signal Processing and Analysis. ed. / A. Neri; H. Babic; S. Loncaric. IEEE Computer Society, 2003. p. 549-554 1296957 (International Symposium on Image and Signal Processing and Analysis, ISPA; Vol. 1).

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

TY - GEN

T1 - A robust singing melody tracker using adaptive round semitones (ARS)

AU - Wang, Chong Kai

AU - Lyu, Ren Yuan

AU - Chiang, Yuang Chin

PY - 2003

Y1 - 2003

N2 - In this paper, an approach for melody tracking is proposed and applied to applications of automatic singing transcription. The melody tracker is based on adaptive round semitones (ARS) algorithm, which converts a pitch contour of singing voice to a sequence of music notes. The pitch of singing voice is usually much more unstable than that of musical instruments. A poor-skilled singer may generate voice with even worse pitch correctness. ARS deals with these issues by using a statistic model, which predicts singers' tune scale of the current note dynamically. Compared with the other approaches, ARS achieves the lowest error rate for poor singers and seems much more insensitive to the diversity of singers' singing skills. Furthermore, by adding on the transcription process a heuristic music grammar constraints based on music theory, the error rate can be reduced 20.5%, which beats all the other approaches mentioned in the other literatures.

AB - In this paper, an approach for melody tracking is proposed and applied to applications of automatic singing transcription. The melody tracker is based on adaptive round semitones (ARS) algorithm, which converts a pitch contour of singing voice to a sequence of music notes. The pitch of singing voice is usually much more unstable than that of musical instruments. A poor-skilled singer may generate voice with even worse pitch correctness. ARS deals with these issues by using a statistic model, which predicts singers' tune scale of the current note dynamically. Compared with the other approaches, ARS achieves the lowest error rate for poor singers and seems much more insensitive to the diversity of singers' singing skills. Furthermore, by adding on the transcription process a heuristic music grammar constraints based on music theory, the error rate can be reduced 20.5%, which beats all the other approaches mentioned in the other literatures.

KW - Algorithm design and analysis

KW - Error analysis

KW - Instruments

KW - Multimedia databases

KW - Multiple signal classification

KW - Predictive models

KW - Robustness

KW - Signal processing algorithms

KW - Software algorithms

KW - Statistics

UR - https://www.scopus.com/pages/publications/84892251330

U2 - 10.1109/ISPA.2003.1296957

DO - 10.1109/ISPA.2003.1296957

M3 - 会议稿件

AN - SCOPUS:84892251330

T3 - International Symposium on Image and Signal Processing and Analysis, ISPA

SP - 549

EP - 554

BT - ISPA 2003 - Proceedings of the 3rd International Symposium on Image and Signal Processing and Analysis

A2 - Neri, A.

A2 - Babic, H.

A2 - Loncaric, S.

PB - IEEE Computer Society

T2 - 3rd International Symposium on Image and Signal Processing and Analysis, ISPA 2003

Y2 - 18 September 2003 through 20 September 2003

ER -

Wang CK, Lyu RY, Chiang YC. A robust singing melody tracker using adaptive round semitones (ARS). In Neri A, Babic H, Loncaric S, editors, ISPA 2003 - Proceedings of the 3rd International Symposium on Image and Signal Processing and Analysis. IEEE Computer Society. 2003. p. 549-554. 1296957. (International Symposium on Image and Signal Processing and Analysis, ISPA). doi: 10.1109/ISPA.2003.1296957

A robust singing melody tracker using adaptive round semitones (ARS)

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this