Details
| Original language | English |
|---|---|
| Pages (from-to) | 213-226 |
| Number of pages | 14 |
| Journal | CEUR Workshop Proceedings |
| Volume | 3341 |
| Publication status | Published - 11 Feb 2023 |
| Event | LWDA 2022 Workshops: FGWM, FGKD, and FGDB - Hildesheim, Germany Duration: 5 Oct 2022 → 7 Oct 2022 |
Abstract
Various versions of musical works are published on YouTube, such as remixes or reaction videos. While some research has focused on tasks like audio-based version identification of these videos, it is still unclear how to effectively retrieve a large amount of relevant versions with textual queries. In this paper, we formulate search queries with YouTube search suggestions, evaluate these based on multiple dimensions and compute optimal ranks of queries on work-level. We show that queries containing the artist string retrieve results with higher relevance, but have higher overlaps. Additionally, we demonstrate that the amount of reasonable queries can be increased by applying frequently suggested expansions to works which tend to contextualize queries to the music domain.
Keywords
- audio based version identification, music on youtube, query formulation
ASJC Scopus subject areas
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: CEUR Workshop Proceedings, Vol. 3341, 11.02.2023, p. 213-226.
Research output: Contribution to journal › Conference article › Research › peer review
}
TY - JOUR
T1 - Music Version Retrieval from YouTube
T2 - LWDA 2022 Workshops: FGWM, FGKD, and FGDB
AU - Hachmeier, Simon
AU - Jäschke, Robert
AU - Saadatdoorabi, Hadi
PY - 2023/2/11
Y1 - 2023/2/11
N2 - Various versions of musical works are published on YouTube, such as remixes or reaction videos. While some research has focused on tasks like audio-based version identification of these videos, it is still unclear how to effectively retrieve a large amount of relevant versions with textual queries. In this paper, we formulate search queries with YouTube search suggestions, evaluate these based on multiple dimensions and compute optimal ranks of queries on work-level. We show that queries containing the artist string retrieve results with higher relevance, but have higher overlaps. Additionally, we demonstrate that the amount of reasonable queries can be increased by applying frequently suggested expansions to works which tend to contextualize queries to the music domain.
AB - Various versions of musical works are published on YouTube, such as remixes or reaction videos. While some research has focused on tasks like audio-based version identification of these videos, it is still unclear how to effectively retrieve a large amount of relevant versions with textual queries. In this paper, we formulate search queries with YouTube search suggestions, evaluate these based on multiple dimensions and compute optimal ranks of queries on work-level. We show that queries containing the artist string retrieve results with higher relevance, but have higher overlaps. Additionally, we demonstrate that the amount of reasonable queries can be increased by applying frequently suggested expansions to works which tend to contextualize queries to the music domain.
KW - audio based version identification
KW - music on youtube
KW - query formulation
UR - http://www.scopus.com/inward/record.url?scp=85148603357&partnerID=8YFLogxK
M3 - Conference article
AN - SCOPUS:85148603357
VL - 3341
SP - 213
EP - 226
JO - CEUR Workshop Proceedings
JF - CEUR Workshop Proceedings
SN - 1613-0073
Y2 - 5 October 2022 through 7 October 2022
ER -