IEICE TRANSACTIONS on Information
Multi-Scale Chroma n-Gram Indexing for Cover Song Identification
Summary :
To enhance cover song identification accuracy on a large-size music archive, a song-level feature summarization method is proposed by using multi-scale representation. The chroma n-grams are extracted in multiple scales to cope with both global and local tempo changes. We derive index from the extracted n-grams by clustering to reduce storage and computation for DB search. Experiments on the widely used music datasets confirmed that the proposed method achieves the state-of-the-art accuracy while reducing cost for cover song search.
- Publication
- IEICE TRANSACTIONS on Information Vol.E103-D No.1 pp.59-62
- Publication Date
- 2020/01/01
- Publicized
- 2019/10/23
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2019MUL0001
- Type of Manuscript
- Special Section LETTER (Special Section on Enriched Multimedia — Application of Multimedia Technology and Its Security —)
- Category
Authors
Jin S. SEO
Gangneung-Wonju National University
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Jin S. SEO, "Multi-Scale Chroma n-Gram Indexing for Cover Song Identification" in IEICE TRANSACTIONS on Information,
vol. E103-D, no. 1, pp. 59-62, January 2020, doi: 10.1587/transinf.2019MUL0001.
Abstract: To enhance cover song identification accuracy on a large-size music archive, a song-level feature summarization method is proposed by using multi-scale representation. The chroma n-grams are extracted in multiple scales to cope with both global and local tempo changes. We derive index from the extracted n-grams by clustering to reduce storage and computation for DB search. Experiments on the widely used music datasets confirmed that the proposed method achieves the state-of-the-art accuracy while reducing cost for cover song search.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2019MUL0001/_p
Copy
@ARTICLE{e103-d_1_59,
author={Jin S. SEO, },
journal={IEICE TRANSACTIONS on Information},
title={Multi-Scale Chroma n-Gram Indexing for Cover Song Identification},
year={2020},
volume={E103-D},
number={1},
pages={59-62},
abstract={To enhance cover song identification accuracy on a large-size music archive, a song-level feature summarization method is proposed by using multi-scale representation. The chroma n-grams are extracted in multiple scales to cope with both global and local tempo changes. We derive index from the extracted n-grams by clustering to reduce storage and computation for DB search. Experiments on the widely used music datasets confirmed that the proposed method achieves the state-of-the-art accuracy while reducing cost for cover song search.},
keywords={},
doi={10.1587/transinf.2019MUL0001},
ISSN={1745-1361},
month={January},}
Copy
TY - JOUR
TI - Multi-Scale Chroma n-Gram Indexing for Cover Song Identification
T2 - IEICE TRANSACTIONS on Information
SP - 59
EP - 62
AU - Jin S. SEO
PY - 2020
DO - 10.1587/transinf.2019MUL0001
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E103-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2020
AB - To enhance cover song identification accuracy on a large-size music archive, a song-level feature summarization method is proposed by using multi-scale representation. The chroma n-grams are extracted in multiple scales to cope with both global and local tempo changes. We derive index from the extracted n-grams by clustering to reduce storage and computation for DB search. Experiments on the widely used music datasets confirmed that the proposed method achieves the state-of-the-art accuracy while reducing cost for cover song search.
ER -
English
