{"id":{"repo_id":"humboldt-diss","oai_identifier":"oai:edoc.hu-berlin.de:18452/36156"},"canonical_url":"https://search.dev.ndltd.org/etd/humboldt-diss/oai:edoc.hu-berlin.de:18452/36156","repository":{"repo_id":"humboldt-diss","name":"Humboldt Universität zu Berlin","base_url":"https://edoc.hu-berlin.de/server/oai/request"},"display":{"title":"A comparison of approaches for processing the time dimension in automatic cover song identification","abstract":"This master’s thesis compares different approaches for processing the time dimension in automatic Cover Song Identification (CSI). Six Time Handling Approaches (THAs) are conceptualized based on existing literature. To test the THA’s impact on cover song prediction performance, a two-phased research strategy is chosen. During the exploratory phase, song pairs are compared qualitatively, while the subsequent retrieval phase evaluates different THAs in a testing environment using various evaluation metrics. While the exploratory phase yields promising results for some THAs, the baseline employed during the retrieval phase cannot be outperformed. The results qualitatively show that longer chunk lengths in THAs typically lead to better prediction performance and are more suited for pairwise comparison than for large-scale retrieval tasks.","abstract_html":"This master’s thesis compares different approaches for processing the time dimension in automatic Cover Song Identification (CSI). Six Time Handling Approaches (THAs) are conceptualized based on existing literature. To test the THA’s impact on cover song prediction performance, a two-phased research strategy is chosen. During the exploratory phase, song pairs are compared qualitatively, while the subsequent retrieval phase evaluates different THAs in a testing environment using various evaluation metrics. While the exploratory phase yields promising results for some THAs, the baseline employed during the retrieval phase cannot be outperformed. The results qualitatively show that longer chunk lengths in THAs typically lead to better prediction performance and are more suited for pairwise comparison than for large-scale retrieval tasks.","abstract_has_math":false,"creators":["Heigenhauser, Jonas"],"institution":"Humboldt-Universität zu Berlin","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-11-24","date_published":"2025-11-24","updated_at":"2026-08-21T16:45:17Z","subjects":["machine learning","information retrieval","music information retrieval","cover song identification","audio analysis","music representation","spectrogram"],"languages":["eng"],"rights":["(CC BY-NC-ND 4.0) Attribution-NonCommercial-NoDerivatives 4.0 International"],"rights_urls":["https://creativecommons.org/licenses/by-nc-nd/4.0/"],"identifier_entries":[{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.18452/35505"],"render_values":[{"text":"https://doi.org/10.18452/35505","href":"https://doi.org/10.18452/35505","code":true}]}]},"links":{"outbound_url":"https://edoc.hu-berlin.de/18452/36156","outbound_label":"Repository record","outbound_source":"dc:identifier.uri"},"source_record":{"url":"https://edoc.hu-berlin.de/server/oai/request?verb=GetRecord&metadataPrefix=dim&identifier=oai%3Aedoc.hu-berlin.de%3A18452%2F36156","prefix":"dim"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Heigenhauser, Jonas"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-11-24T08:34:28Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-11-24T08:34:28Z"]},{"key":"dc:date.issued","label":"Date","values":["2025-11-24"]},{"key":"dc:publisher","label":"Institution","values":["Humboldt-Universität zu Berlin"]},{"key":"dc:type","label":"Dc Type","values":["masterThesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["machine learning","information retrieval","music information retrieval","cover song identification","audio analysis","music representation","spectrogram"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["(CC BY-NC-ND 4.0) Attribution-NonCommercial-NoDerivatives 4.0 International"]},{"key":"dc:rights.uri","label":"Rights URI","values":["https://creativecommons.org/licenses/by-nc-nd/4.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.18452/35505"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://edoc.hu-berlin.de/18452/36156"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Diese Veröffentlichung geht zurück auf eine Masterarbeit im Studiengang Information Science, M. A. an der Humboldt-Universität zu Berlin aus dem Jahr 2024."]},{"key":"dc:description.abstract","label":"Abstract","values":["This master’s thesis compares different approaches for processing the time dimension in automatic Cover Song Identification (CSI). Six Time Handling Approaches (THAs) are conceptualized based on existing literature. To test the THA’s impact on cover song prediction performance, a two-phased research strategy is chosen. During the exploratory phase, song pairs are compared qualitatively, while the subsequent retrieval phase evaluates different THAs in a testing environment using various evaluation metrics. While the exploratory phase yields promising results for some THAs, the baseline employed during the retrieval phase cannot be outperformed. The results qualitatively show that longer chunk lengths in THAs typically lead to better prediction performance and are more suited for pairwise comparison than for large-scale retrieval tasks."]},{"key":"dc:title","label":"Title","values":["A comparison of approaches for processing the time dimension in automatic cover song identification"]}]}],"canonical_facts":{"dc:creator":["Heigenhauser, Jonas"],"dc:date.accessioned":["2025-11-24T08:34:28Z"],"dc:date.available":["2025-11-24T08:34:28Z"],"dc:date.issued":["2025-11-24"],"dc:description":["Diese Veröffentlichung geht zurück auf eine Masterarbeit im Studiengang Information Science, M. A. an der Humboldt-Universität zu Berlin aus dem Jahr 2024."],"dc:description.abstract":["This master’s thesis compares different approaches for processing the time dimension in automatic Cover Song Identification (CSI). Six Time Handling Approaches (THAs) are conceptualized based on existing literature. To test the THA’s impact on cover song prediction performance, a two-phased research strategy is chosen. During the exploratory phase, song pairs are compared qualitatively, while the subsequent retrieval phase evaluates different THAs in a testing environment using various evaluation metrics. While the exploratory phase yields promising results for some THAs, the baseline employed during the retrieval phase cannot be outperformed. The results qualitatively show that longer chunk lengths in THAs typically lead to better prediction performance and are more suited for pairwise comparison than for large-scale retrieval tasks."],"dc:identifier.doi":["https://doi.org/10.18452/35505"],"dc:identifier.uri":["https://edoc.hu-berlin.de/18452/36156"],"dc:language.iso":["eng"],"dc:publisher":["Humboldt-Universität zu Berlin"],"dc:rights":["(CC BY-NC-ND 4.0) Attribution-NonCommercial-NoDerivatives 4.0 International"],"dc:rights.uri":["https://creativecommons.org/licenses/by-nc-nd/4.0/"],"dc:subject":["machine learning","information retrieval","music information retrieval","cover song identification","audio analysis","music representation","spectrogram"],"dc:title":["A comparison of approaches for processing the time dimension in automatic cover song identification"],"dc:type":["masterThesis"]},"updated_at":"2026-08-21T16:45:17Z"}