{"id":"https://openalex.org/W4283652003","doi":"https://doi.org/10.21437/interspeech.2022-11137","title":"Deformable CNN and Imbalance-Aware Feature Learning for Singing Technique Classification","display_name":"Deformable CNN and Imbalance-Aware Feature Learning for Singing Technique Classification","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4283652003","doi":"https://doi.org/10.21437/interspeech.2022-11137"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-11137","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11137","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101025232","display_name":"Yuya Yamamoto","orcid":null},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yuya Yamamoto","raw_affiliation_strings":["Doctoral Program in Informatics, University of Tsukuba, Japan"],"affiliations":[{"raw_affiliation_string":"Doctoral Program in Informatics, University of Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056437111","display_name":"Juhan Nam","orcid":"https://orcid.org/0000-0003-2664-2119"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Juhan Nam","raw_affiliation_strings":["Graduate School of Culture Technology, KAIST, South Korea"],"affiliations":[{"raw_affiliation_string":"Graduate School of Culture Technology, KAIST, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008403512","display_name":"Hiroko Terasawa","orcid":null},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroko Terasawa","raw_affiliation_strings":["Doctoral Program in Informatics, University of Tsukuba, Japan"],"affiliations":[{"raw_affiliation_string":"Doctoral Program in Informatics, University of Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101025232"],"corresponding_institution_ids":["https://openalex.org/I146399215"],"apc_list":null,"apc_paid":null,"fwci":0.6137,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.64676145,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2778","last_page":"2782"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9980000257492065,"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":0.9901999831199646,"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":0.7626290321350098},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.6432036757469177},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5714064836502075},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.569968581199646},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.48349764943122864},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4822891056537628},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46856075525283813},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.0350765585899353}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7626290321350098},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.6432036757469177},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5714064836502075},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.569968581199646},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.48349764943122864},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4822891056537628},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46856075525283813},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0350765585899353},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-11137","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11137","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2015452969","https://openalex.org/W2437181147","https://openalex.org/W2440599146","https://openalex.org/W2601564443","https://openalex.org/W2799262584","https://openalex.org/W2903032817","https://openalex.org/W2903303702","https://openalex.org/W2906098386","https://openalex.org/W2936621055","https://openalex.org/W2962907269","https://openalex.org/W2963691377","https://openalex.org/W2963703197","https://openalex.org/W2966926453","https://openalex.org/W2995197345","https://openalex.org/W3095570043","https://openalex.org/W3131287090","https://openalex.org/W3169483174","https://openalex.org/W4286857487","https://openalex.org/W4287194661"],"related_works":["https://openalex.org/W4386159726","https://openalex.org/W2601157893","https://openalex.org/W2131735617","https://openalex.org/W2373006798","https://openalex.org/W2056912418","https://openalex.org/W2123759770","https://openalex.org/W2033213769","https://openalex.org/W4312376745","https://openalex.org/W2136016640","https://openalex.org/W2082269393"],"abstract_inverted_index":{"Singing":[0],"techniques":[1,38],"are":[2,44,53],"used":[3],"for":[4],"expressive":[5],"vocal":[6],"performances":[7],"by":[8,46,122],"employing":[9],"temporal":[10],"fluctuations":[11,35],"of":[12,20,29,74],"the":[13,15,21,34,75,79,89,92,96,105,114,118,128],"timbre,":[14],"pitch,":[16],"and":[17,43,49,78,110,116],"other":[18],"components":[19],"voice.Their":[22],"classification":[23,97,129],"is":[24,102],"a":[25,40,61,82,123],"challenging":[26],"task,":[27],"because":[28],"mainly":[30],"two":[31,107],"factors:":[32],"1)":[33,91],"in":[36],"singing":[37],"have":[39],"wide":[41],"variety":[42],"affected":[45],"many":[47],"factors":[48],"2)":[50,111],"existing":[51],"datasets":[52],"imbalanced.To":[54],"deal":[55],"with":[56,71],"these":[57],"problems,":[58],"we":[59],"developed":[60],"novel":[62],"audio":[63],"feature":[64,76],"learning":[65],"method":[66],"based":[67],"on":[68],"deformable":[69,93],"convolution":[70,94],"decoupled":[72],"training":[73],"extractor":[77],"classifier":[80,115],"using":[81],"classweighted":[83],"loss":[84,120],"function.The":[85],"experimental":[86],"results":[87],"show":[88],"following:":[90],"improves":[95],"results,":[98],"particularly":[99],"when":[100],"it":[101],"applied":[103],"to":[104],"last":[106],"convolutional":[108],"layers,":[109],"both":[112],"re-training":[113],"weighting":[117],"cross-entropy":[119],"function":[121],"smoothed":[124],"inverse":[125],"frequency":[126],"enhance":[127],"performance.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}