Details
| Original language | English |
|---|---|
| Title of host publication | LWDA 2023 |
| Subtitle of host publication | Lernen, Wissen, Daten, Analysen 2023 |
| Pages | 359-371 |
| Number of pages | 13 |
| Volume | 3630 |
| Publication status | Published - 2023 |
| Event | 2023 Learning. Knowledge. Data. Analytics, LWDA 2023 - Marburg, Germany Duration: 9 Oct 2023 → 11 Oct 2023 |
Publication series
| Name | CEUR Workshop Proceedings |
|---|---|
| Publisher | CEUR Workshop Proceedings |
| Volume | 3630 |
| ISSN (Print) | 1613-0073 |
Abstract
The task of cover song identification (CSI) deals with the automatic matching of audio recordings by modeling musical similarity. CSI is of high relevance in the context of applications such as copyright infringement detection on online video platforms. Since online videos include metadata (eg. video titles, descriptions), one could leverage it for more effective CSI in practice. In this work, we experiment with state-of-the-art models of CSI and entity matching in a Co-Training ensemble. Our results outline slight improvements of the entity matching model. We further outline some suggestions for improvements of our approach to overcome the issue of overfitting CSI models which we observed.
Keywords
- co-training, cover song identification, entity matching
ASJC Scopus subject areas
- Computer Science(all)
- General Computer Science
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
LWDA 2023: Lernen, Wissen, Daten, Analysen 2023. Vol. 3630 2023. p. 359-371 (CEUR Workshop Proceedings; Vol. 3630).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Cover Song Identification in Practice with Multimodal Co-Training
AU - Hachmeier, Simon
AU - Jäschke, Robert
PY - 2023
Y1 - 2023
N2 - The task of cover song identification (CSI) deals with the automatic matching of audio recordings by modeling musical similarity. CSI is of high relevance in the context of applications such as copyright infringement detection on online video platforms. Since online videos include metadata (eg. video titles, descriptions), one could leverage it for more effective CSI in practice. In this work, we experiment with state-of-the-art models of CSI and entity matching in a Co-Training ensemble. Our results outline slight improvements of the entity matching model. We further outline some suggestions for improvements of our approach to overcome the issue of overfitting CSI models which we observed.
AB - The task of cover song identification (CSI) deals with the automatic matching of audio recordings by modeling musical similarity. CSI is of high relevance in the context of applications such as copyright infringement detection on online video platforms. Since online videos include metadata (eg. video titles, descriptions), one could leverage it for more effective CSI in practice. In this work, we experiment with state-of-the-art models of CSI and entity matching in a Co-Training ensemble. Our results outline slight improvements of the entity matching model. We further outline some suggestions for improvements of our approach to overcome the issue of overfitting CSI models which we observed.
KW - co-training
KW - cover song identification
KW - entity matching
UR - http://www.scopus.com/inward/record.url?scp=85184666541&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85184666541
VL - 3630
T3 - CEUR Workshop Proceedings
SP - 359
EP - 371
BT - LWDA 2023
T2 - 2023 Learning. Knowledge. Data. Analytics, LWDA 2023
Y2 - 9 October 2023 through 11 October 2023
ER -