{"id":{"repo_id":"csusb","oai_identifier":"oai:scholarworks.lib.csusb.edu:etd-3526"},"canonical_url":"https://search.ndltd.org/etd/csusb/oai:scholarworks.lib.csusb.edu:etd-3526","repository":{"repo_id":"csusb","name":"CSUniversity San Bernardino","base_url":"https://scholarworks.lib.csusb.edu/do/oai/"},"display":{"title":"Predicting Music Origin with Deep Learning","abstract":"This project explores the usage of a late fusion deep learning architecture to predict the geographic origin of music. Mel-Frequency Cepstral Coefficients (MFCCs) and the language of the music sample are used as features. MFCCs were extracted from audio files to capture sound features. The language was identified using OpenAI’s Whisper model to provide additional context. A late fusion neural network architecture combining Long Short-Term Memory (LSTM) layers for sequential MFCC input and dense layers for non-sequential language features were employed to support both classification and regression tasks. The classification model achieved an accuracy of 33.03% across 56 countries or territories, substantially outperforming the random baseline (1.79%). The regression model produced a Mean Great-Circle Error (MGCE) of 2,754.83 km. While regression offers more flexibility for geographic estimation, classification demonstrated a more promising performance with the current dataset. This work highlights the potential of multimodal learning in music-origin prediction.","abstract_html":"This project explores the usage of a late fusion deep learning architecture to predict the geographic origin of music. Mel-Frequency Cepstral Coefficients (MFCCs) and the language of the music sample are used as features. MFCCs were extracted from audio files to capture sound features. The language was identified using OpenAI’s Whisper model to provide additional context. A late fusion neural network architecture combining Long Short-Term Memory (LSTM) layers for sequential MFCC input and dense layers for non-sequential language features were employed to support both classification and regression tasks. The classification model achieved an accuracy of 33.03% across 56 countries or territories, substantially outperforming the random baseline (1.79%). The regression model produced a Mean Great-Circle Error (MGCE) of 2,754.83 km. While regression offers more flexibility for geographic estimation, classification demonstrated a more promising performance with the current dataset. This work highlights the potential of multimodal learning in music-origin prediction.","abstract_has_math":false,"creators":["Ladanyi, Fruzsina"],"institution":null,"degree_name":"Master of Science in Computer Science","degree_level":"Project","degree_discipline":"School of Computer Science and Engineering","degree_department":null,"school":null,"contributors":["Haiyan Qiao"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T08:10:11Z","subjects":["multimodal learning","deep learning","MFCC","LSTM","geographic classification","MIR","Computer Sciences","Data Science","Ethnomusicology","Music","Other Computer Sciences","Other Music"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://scholarworks.lib.csusb.edu/etd/2303","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://scholarworks.lib.csusb.edu/etd/2303","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://scholarworks.lib.csusb.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Ascholarworks.lib.csusb.edu%3Aetd-3526","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Haiyan Qiao"]},{"key":"dc:creator","label":"Author","values":["Ladanyi, Fruzsina"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2025-07-13T07:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2025-08-01T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["School of Computer Science and Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Project"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science in Computer Science"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["multimodal learning","deep learning","MFCC","LSTM","geographic classification","MIR","Computer Sciences","Data Science","Ethnomusicology","Music","Other Computer Sciences","Other Music"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://scholarworks.lib.csusb.edu/etd/2303"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["This project explores the usage of a late fusion deep learning architecture to predict the geographic origin of music. Mel-Frequency Cepstral Coefficients (MFCCs) and the language of the music sample are used as features. MFCCs were extracted from audio files to capture sound features. The language was identified using OpenAI’s Whisper model to provide additional context. A late fusion neural network architecture combining Long Short-Term Memory (LSTM) layers for sequential MFCC input and dense layers for non-sequential language features were employed to support both classification and regression tasks. The classification model achieved an accuracy of 33.03% across 56 countries or territories, substantially outperforming the random baseline (1.79%). The regression model produced a Mean Great-Circle Error (MGCE) of 2,754.83 km. While regression offers more flexibility for geographic estimation, classification demonstrated a more promising performance with the current dataset. This work highlights the potential of multimodal learning in music-origin prediction."]},{"key":"dc:title","label":"Title","values":["Predicting Music Origin with Deep Learning"]}]}],"canonical_facts":{"dc:contributor":["Haiyan Qiao"],"dc:creator":["Ladanyi, Fruzsina"],"dc:date.available":["2025-07-13T07:00:00Z"],"dc:date.created":["2025-08-01T07:00:00Z"],"dc:description.abstract":["This project explores the usage of a late fusion deep learning architecture to predict the geographic origin of music. Mel-Frequency Cepstral Coefficients (MFCCs) and the language of the music sample are used as features. MFCCs were extracted from audio files to capture sound features. The language was identified using OpenAI’s Whisper model to provide additional context. A late fusion neural network architecture combining Long Short-Term Memory (LSTM) layers for sequential MFCC input and dense layers for non-sequential language features were employed to support both classification and regression tasks. The classification model achieved an accuracy of 33.03% across 56 countries or territories, substantially outperforming the random baseline (1.79%). The regression model produced a Mean Great-Circle Error (MGCE) of 2,754.83 km. While regression offers more flexibility for geographic estimation, classification demonstrated a more promising performance with the current dataset. This work highlights the potential of multimodal learning in music-origin prediction."],"dc:identifier":["https://scholarworks.lib.csusb.edu/etd/2303"],"dc:subject":["multimodal learning","deep learning","MFCC","LSTM","geographic classification","MIR","Computer Sciences","Data Science","Ethnomusicology","Music","Other Computer Sciences","Other Music"],"dc:title":["Predicting Music Origin with Deep Learning"],"thesis:degree_discipline":["School of Computer Science and Engineering"],"thesis:degree_level":["Project"],"thesis:degree_name":["Master of Science in Computer Science"]},"updated_at":"2026-11-19T08:10:11Z"}