On the robustness of cover version identification models: a study using cover versions from YouTube
Introduction. Recent advances in cover version identification have shown great success. However, models are usually tested on a fixed set of datasets which are relying on the online cover version database SecondHandSongs. It is unclear how well models perform on cover versions on online video platf...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
University of Borås
2025-03-01
|
| Series: | Information Research: An International Electronic Journal |
| Subjects: | |
| Online Access: | https://publicera.kb.se/ir/article/view/47077 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850253550243807232 |
|---|---|
| author | Simon Hachmeier Robert Jäschke |
| author_facet | Simon Hachmeier Robert Jäschke |
| author_sort | Simon Hachmeier |
| collection | DOAJ |
| description |
Introduction. Recent advances in cover version identification have shown great success. However, models are usually tested on a fixed set of datasets which are relying on the online cover version database SecondHandSongs. It is unclear how well models perform on cover versions on online video platforms, which might exhibit alterations that are not expected.
Method. We annotate a subset of versions from YouTube sampled by a multi-modal uncertainty sampling approach and evaluate state-of-the-art cover version identification models.
Results. We find that existing models achieve significantly lower ranking performance on our dataset compared to a community dataset. We additionally measure the performance of different types of versions (e.g., instrumental versions) and find several types that are particularly hard to rank. Lastly, we provide a taxonomy of alterations in cover versions on the web.
Conclusions. We found that research in cover version identification shall be less dependent on SecondHandSongs but rather on more diverse datasets.
|
| format | Article |
| id | doaj-art-fb53a865cec948a2b53225402ff3aeba |
| institution | OA Journals |
| issn | 1368-1613 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | University of Borås |
| record_format | Article |
| series | Information Research: An International Electronic Journal |
| spelling | doaj-art-fb53a865cec948a2b53225402ff3aeba2025-08-20T01:57:20ZengUniversity of BoråsInformation Research: An International Electronic Journal1368-16132025-03-0130iConf10.47989/ir30iConf47077On the robustness of cover version identification models: a study using cover versions from YouTubeSimon Hachmeier0Robert Jäschke1Humboldt-Universität zu Berlin, GermanyHumboldt-Universität zu Berlin, Germany Introduction. Recent advances in cover version identification have shown great success. However, models are usually tested on a fixed set of datasets which are relying on the online cover version database SecondHandSongs. It is unclear how well models perform on cover versions on online video platforms, which might exhibit alterations that are not expected. Method. We annotate a subset of versions from YouTube sampled by a multi-modal uncertainty sampling approach and evaluate state-of-the-art cover version identification models. Results. We find that existing models achieve significantly lower ranking performance on our dataset compared to a community dataset. We additionally measure the performance of different types of versions (e.g., instrumental versions) and find several types that are particularly hard to rank. Lastly, we provide a taxonomy of alterations in cover versions on the web. Conclusions. We found that research in cover version identification shall be less dependent on SecondHandSongs but rather on more diverse datasets. https://publicera.kb.se/ir/article/view/47077cover songmusicretrieval longtail |
| spellingShingle | Simon Hachmeier Robert Jäschke On the robustness of cover version identification models: a study using cover versions from YouTube Information Research: An International Electronic Journal cover song music retrieval longtail |
| title | On the robustness of cover version identification models: a study using cover versions from YouTube |
| title_full | On the robustness of cover version identification models: a study using cover versions from YouTube |
| title_fullStr | On the robustness of cover version identification models: a study using cover versions from YouTube |
| title_full_unstemmed | On the robustness of cover version identification models: a study using cover versions from YouTube |
| title_short | On the robustness of cover version identification models: a study using cover versions from YouTube |
| title_sort | on the robustness of cover version identification models a study using cover versions from youtube |
| topic | cover song music retrieval longtail |
| url | https://publicera.kb.se/ir/article/view/47077 |
| work_keys_str_mv | AT simonhachmeier ontherobustnessofcoverversionidentificationmodelsastudyusingcoverversionsfromyoutube AT robertjaschke ontherobustnessofcoverversionidentificationmodelsastudyusingcoverversionsfromyoutube |