{"id":"https://openalex.org/W3104737411","doi":"https://doi.org/10.21437/interspeech.2021-636","title":"Knowledge Distillation for Singing Voice Detection","display_name":"Knowledge Distillation for Singing Voice Detection","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3104737411","doi":"https://doi.org/10.21437/interspeech.2021-636","mag":"3104737411"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-636","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-636","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2011.04297","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110796601","display_name":"Soumava Paul","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Soumava Paul","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017335381","display_name":"Gurunath Reddy M","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gurunath Reddy M","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048234263","display_name":"K. Sreenivasa Rao","orcid":"https://orcid.org/0000-0002-2186-0419"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"K. Sreenivasa Rao","raw_affiliation_strings":["Indian Institute of Technology Kharagpur, Kharagpur, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Kharagpur, Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011440310","display_name":"Partha Pratim Das","orcid":"https://orcid.org/0000-0003-1435-6051"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Partha Pratim Das","raw_affiliation_strings":["Indian Institute of Technology Kharagpur, Kharagpur, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Kharagpur, Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3088,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.507063,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"4159","last_page":"4163"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8082779049873352},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.638491690158844},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6297663450241089},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.601550817489624},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5786793231964111},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5443241000175476},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5362253785133362},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5260374546051025},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4789343774318695},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.473499596118927},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.46269330382347107},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3298816978931427}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8082779049873352},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.638491690158844},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6297663450241089},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.601550817489624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5786793231964111},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5443241000175476},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5362253785133362},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5260374546051025},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4789343774318695},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.473499596118927},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.46269330382347107},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3298816978931427},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2021-636","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-636","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2011.04297","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.04297","pdf_url":"https://arxiv.org/pdf/2011.04297","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"mag:3104737411","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2011.04297","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2011.04297","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.04297","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2011.04297","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.04297","pdf_url":"https://arxiv.org/pdf/2011.04297","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3104737411.pdf","grobid_xml":"https://content.openalex.org/works/W3104737411.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W144548647","https://openalex.org/W1570504315","https://openalex.org/W1583001605","https://openalex.org/W1821462560","https://openalex.org/W1921523184","https://openalex.org/W2007664495","https://openalex.org/W2064675550","https://openalex.org/W2098796164","https://openalex.org/W2100772705","https://openalex.org/W2406220897","https://openalex.org/W2406222150","https://openalex.org/W2406972062","https://openalex.org/W2806313776","https://openalex.org/W2911803042","https://openalex.org/W2996569511"],"related_works":["https://openalex.org/W3197900571","https://openalex.org/W2750784772","https://openalex.org/W3153243387","https://openalex.org/W3210574093","https://openalex.org/W3205825741","https://openalex.org/W3081030157","https://openalex.org/W3004091221","https://openalex.org/W2787017828","https://openalex.org/W2904170036","https://openalex.org/W2997336365","https://openalex.org/W3157390534","https://openalex.org/W3195877590","https://openalex.org/W2787751390","https://openalex.org/W3047564907","https://openalex.org/W3092631455","https://openalex.org/W2903462692","https://openalex.org/W2928413680","https://openalex.org/W3081899492","https://openalex.org/W3159778524","https://openalex.org/W3089361613"],"abstract_inverted_index":{"Singing":[0],"Voice":[1],"Detection":[2],"(SVD)":[3],"has":[4,150],"been":[5,153,160],"an":[6],"active":[7],"area":[8],"of":[9,58,85,133,142],"research":[10],"in":[11,32,83,103,135],"music":[12,136],"information":[13,137],"retrieval":[14],"(MIR).":[15],"Currently,":[16],"two":[17],"deep":[18,104],"neural":[19],"network-based":[20],"methods,":[21],"one":[22],"based":[23],"on":[24,29,48,73],"CNN":[25,62],"and":[26,44,63,67,87],"the":[27,39,119,130,140],"other":[28],"RNN,":[30],"exist":[31],"literature":[33,106],"that":[34],"learn":[35],"optimized":[36],"features":[37],"for":[38,61,65,71,147],"voice":[40],"detection":[41],"(VD)":[42],"task":[43],"achieve":[45],"state-of-the-art":[46],"performance":[47],"common":[49],"datasets.":[50],"Both":[51],"these":[52],"models":[53],"have":[54,159],"a":[55,113,125],"huge":[56],"number":[57],"parameters":[59],"(1.4M":[60],"65.7K":[64],"RNN)":[66],"hence":[68],"not":[69,151],"suitable":[70],"deployment":[72,149],"devices":[74],"like":[75],"smartphones":[76],"or":[77],"embedded":[78],"sensors":[79],"with":[80],"limited":[81],"capacity":[82],"terms":[84],"memory":[86],"computation":[88],"power.":[89],"The":[90],"most":[91],"popular":[92],"method":[93],"to":[94,109,123,139,162],"address":[95],"this":[96,156,164],"issue":[97,165],"is":[98,121],"known":[99,117],"as":[100,118,169,171],"knowledge":[101,173],"distillation":[102,174],"learning":[105],"(in":[107],"addition":[108],"model":[110,145],"compression)":[111],"where":[112],"large":[114],"pre-trained":[115],"network":[116],"teacher":[120],"used":[122],"train":[124],"smaller":[126],"student":[127],"network.":[128],"Given":[129],"wide":[131],"applications":[132],"SVD":[134],"retrieval,":[138],"best":[141],"our":[143],"knowledge,":[144],"compression":[146],"practical":[148],"yet":[152],"explored.":[154],"In":[155],"paper,":[157],"efforts":[158],"made":[161],"investigate":[163],"using":[166],"both":[167],"conventional":[168],"well":[170],"ensemble":[172],"techniques.":[175]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}