{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/104915"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/104915","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Exploring deep learning based methods for information retrieval in Indian classical music","abstract":"A vital aspect of Indian Classical Music (ICM) is Raga, which serves as a melodic framework for compositions and improvisations alike. Raga Recognition is an important music information retrieval task in ICM as it can aid numerous downstream applications ranging from music recommendations to organizing huge music collections. In this work, we propose a deep learning based approach to Raga recognition. Our approach employs efficient pre-possessing and learns temporal sequences in music data using Long Short Term Memory based Recurrent Neural Networks (LSTM-RNN). We train and test the network on smaller sequences sampled from the original audio while the final inference is performed on the audio as a whole. Our method achieves an accuracy of 88.1% and 97 % during inference on the Comp Music Carnatic dataset and its 10 Raga subset respectively making it the state of-the-art for the Raga recognition task. Our approach also enables sequence ranking which aids us in retrieving melodic patterns from a given music data base that are closely related to the presented query sequence.","abstract_html":"A vital aspect of Indian Classical Music (ICM) is Raga, which serves as a melodic framework for compositions and improvisations alike. Raga Recognition is an important music information retrieval task in ICM as it can aid numerous downstream applications ranging from music recommendations to organizing huge music collections. In this work, we propose a deep learning based approach to Raga recognition. Our approach employs efficient pre-possessing and learns temporal sequences in music data using Long Short Term Memory based Recurrent Neural Networks (LSTM-RNN). We train and test the network on smaller sequences sampled from the original audio while the final inference is performed on the audio as a whole. Our method achieves an accuracy of 88.1% and 97 % during inference on the Comp Music Carnatic dataset and its 10 Raga subset respectively making it the state of-the-art for the Raga recognition task. Our approach also enables sequence ranking which aids us in retrieving melodic patterns from a given music data base that are closely related to the presented query sequence.","abstract_has_math":false,"creators":["Madhusudhan, Sathwik Tejaswi"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Industrial Engineering","degree_department":null,"school":null,"contributors":["Chowdhary, Girish","Sreenivas, Ramavarapu"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2019,"date_issued":"2019-08-23T20:01:16Z","date_published":"2019-08-23T20:01:16Z","updated_at":"2026-07-22T22:24:42Z","subjects":["Deep Learning","Machine Learning","Music Information Retrieval"],"languages":["en"],"rights":["Copyright 2019 Sathwik Tejaswi Madhusudhan"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/104915","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Chowdhary, Girish","Sreenivas, Ramavarapu"]},{"key":"dc:creator","label":"Author","values":["Madhusudhan, Sathwik Tejaswi"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2019-08-23T20:01:16Z","2019-04-25","2019-05"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Industrial Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Deep Learning","Machine Learning","Music Information Retrieval"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2019 Sathwik Tejaswi Madhusudhan"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/104915"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["A vital aspect of Indian Classical Music (ICM) is Raga, which serves as a melodic framework for compositions and improvisations alike. Raga Recognition is an important music information retrieval task in ICM as it can aid numerous downstream applications ranging from music recommendations to organizing huge music collections. In this work, we propose a deep learning based approach to Raga recognition. Our approach employs efficient pre-possessing and learns temporal sequences in music data using Long Short Term Memory based Recurrent Neural Networks (LSTM-RNN). We train and test the network on smaller sequences sampled from the original audio while the final inference is performed on the audio as a whole. Our method achieves an accuracy of 88.1% and 97 % during inference on the Comp Music Carnatic dataset and its 10 Raga subset respectively making it the state of-the-art for the Raga recognition task. Our approach also enables sequence ranking which aids us in retrieving melodic patterns from a given music data base that are closely related to the presented query sequence.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2019-08-22 without embargo terms","The student, Sathwik Tejaswi Madhusudhan, accepted the attached license on 2019-04-24 at 01:52.","The student, Sathwik Tejaswi Madhusudhan, submitted this Thesis for approval on 2019-04-24 at 01:56.","This Thesis was approved for publication on 2019-04-25 at 07:55.","DSpace SAF Submission Ingestion Package generated from Vireo submission #13856 on 2019-08-22 at 14:46:20","Made available in DSpace on 2019-08-23T20:01:16Z (GMT). No. of bitstreams: 2 MADHUSUDHAN-THESIS-2019.pdf: 1201012 bytes, checksum: b1159640b80e3336d1529b4c5f0c7182 (MD5) LICENSE.txt: 4224 bytes, checksum: 442583a3355d29d77bbfcf29d479fa36 (MD5) Previous issue date: 2019-04-25"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Exploring deep learning based methods for information retrieval in Indian classical music"]}]}],"canonical_facts":{"dc:contributor":["Chowdhary, Girish","Sreenivas, Ramavarapu"],"dc:creator":["Madhusudhan, Sathwik Tejaswi"],"dc:date":["2019-08-23T20:01:16Z","2019-04-25","2019-05"],"dc:description":["A vital aspect of Indian Classical Music (ICM) is Raga, which serves as a melodic framework for compositions and improvisations alike. Raga Recognition is an important music information retrieval task in ICM as it can aid numerous downstream applications ranging from music recommendations to organizing huge music collections. In this work, we propose a deep learning based approach to Raga recognition. Our approach employs efficient pre-possessing and learns temporal sequences in music data using Long Short Term Memory based Recurrent Neural Networks (LSTM-RNN). We train and test the network on smaller sequences sampled from the original audio while the final inference is performed on the audio as a whole. Our method achieves an accuracy of 88.1% and 97 % during inference on the Comp Music Carnatic dataset and its 10 Raga subset respectively making it the state of-the-art for the Raga recognition task. Our approach also enables sequence ranking which aids us in retrieving melodic patterns from a given music data base that are closely related to the presented query sequence.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2019-08-22 without embargo terms","The student, Sathwik Tejaswi Madhusudhan, accepted the attached license on 2019-04-24 at 01:52.","The student, Sathwik Tejaswi Madhusudhan, submitted this Thesis for approval on 2019-04-24 at 01:56.","This Thesis was approved for publication on 2019-04-25 at 07:55.","DSpace SAF Submission Ingestion Package generated from Vireo submission #13856 on 2019-08-22 at 14:46:20","Made available in DSpace on 2019-08-23T20:01:16Z (GMT). No. of bitstreams: 2 MADHUSUDHAN-THESIS-2019.pdf: 1201012 bytes, checksum: b1159640b80e3336d1529b4c5f0c7182 (MD5) LICENSE.txt: 4224 bytes, checksum: 442583a3355d29d77bbfcf29d479fa36 (MD5) Previous issue date: 2019-04-25"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/104915"],"dc:language":["en"],"dc:rights":["Copyright 2019 Sathwik Tejaswi Madhusudhan"],"dc:subject":["Deep Learning","Machine Learning","Music Information Retrieval"],"dc:title":["Exploring deep learning based methods for information retrieval in Indian classical music"],"dc:type":["text"],"thesis:degree_discipline":["Industrial Engineering"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:42Z"}