リケラボ論文検索は、全国の大学リポジトリにある学位論文・教授論文を一括検索できる論文検索サービスです。

リケラボ 全国の大学リポジトリにある学位論文・教授論文を一括検索するならリケラボ論文検索大学・研究所にある論文を検索できる

リケラボ 全国の大学リポジトリにある学位論文・教授論文を一括検索するならリケラボ論文検索大学・研究所にある論文を検索できる

大学・研究所にある論文を検索できる 「Improved System for Identification of Live Music Performances by Dynamic Time Warping」の論文概要。リケラボ論文検索は、全国の大学リポジトリにある学位論文・教授論文を一括検索できる論文検索サービスです。

コピーが完了しました

URLをコピーしました

論文の公開元へ論文の公開元へ
書き出し

Improved System for Identification of Live Music Performances by Dynamic Time Warping

KAWAMATA, Taisuke HONDA, Ayami MATSUDA, Yoshitatsu 成蹊大学 DOI:info:doi/10.15018/00001279

2021.12.01

概要

The identification of a song performed at a concert, called the "live version," is not yet a popular search among users because of the song possibly having a different arrangement or other modifications, unlike audio searches for an exactly matching song. For live song identification, we examined the application of dynamic time warping to chroma feature series extracted from both studio and live versions of a song. In this paper, we especially focused on measuring the linearity of the warping path. It was evaluated using datasets collected from the internet and the results were compared to those of an existing search service, which showed that the proposed method has the highest accuracy.

この論文で使われている画像

参考文献

so

it may be

as a ring

However,

This work was supported by the Japan Society for the

in the

was female.

To solve this problem,

the parts for all instruments

Acknowledgement

that

the studio and live versions,

the chroma

an octave

song key are not frequent

rearrange

because

features.

Fig. 6 shows

The key of song No.

was male but the live vocalist

No. 4 could not be identified.

beneficial

either.

path of No. 4 was non-linear.

4 was changed

change

not be identified

[1] SoundHound http://www.soundhound.com (Accessed by

buffer

changes

in

the performer

to

1 Dec. 2021)

[2] Shazam https://www.shazam.com (Accessed by 1 Dec.

2021)

used in the song.

[3] L. Marsik, M. Rusek, K. Slaninova, J. Martinovic and J.

Pokorny, "Evaluation of Chord and Chroma Features and

—5—

Dynamic

Time Warping Scores on

Cover

'*" IT 1

Song

Identification Task," Proc. IFIP International Conference

on Computer Information

Systems and Industrial

Management, Vol.61, pp.205-217, May 2017

[4] J. Serra, X. Serra and R. G. Andrzejak, "Cross recurrence

quantification for cover song identification," New Journal

of Physics, Vol.10244, No.9, pp.1-18, Sept 2009

[5] Y. Meron, K. Hirose, "Automatic alignment of a musical

score to performed music," Vol.22,No.3, pp.189-198, Dec

2001

[6] T. Tsai, T. Pratzlich, M. Muller and J. Martinovic,

"Known-Artist Live Song Identification Using Audio

Hashprints," IEEE Transactions on Multimedia, Vol.19,

No.7, pp. 1569-1582, Feb 2017

[7] G. Doras, G. Peeters, "A Prototypical Triplet Loss for

Cover Detection," Proc. IEEE International Conference

on Acoustics, Speech and Signal Processing, pp. 37973801, Apr 2020

[8] librosa, https://librosa.org (Accessed by 1 Apr. 2021)

—6—

''#' U

5P6 $E ii

Vol.58 No.2(2021 .12)

...

参考文献をもっと見る