{"id":"https://openalex.org/W4375869266","doi":"https://doi.org/10.1109/icassp49357.2023.10095669","title":"Phonation Mode Detection in Singing: A Singer Adapted Model","display_name":"Phonation Mode Detection in Singing: A Singer Adapted Model","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869266","doi":"https://doi.org/10.1109/icassp49357.2023.10095669"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095669","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095669","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100328543","display_name":"Yixin Wang","orcid":"https://orcid.org/0000-0002-7330-801X"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Yixin Wang","raw_affiliation_strings":["National University of Singapore,School of Computing,Singapore","Xi&#x2019;an Jiaotong University,MOE KLINNS Lab, Faculty of Electronics and Information Engineering,Xi&#x2019;an,China,710049","School of Computing, National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,School of Computing,Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Xi&#x2019;an Jiaotong University,MOE KLINNS Lab, Faculty of Electronics and Information Engineering,Xi&#x2019;an,China,710049","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100323695","display_name":"Wei Wei","orcid":"https://orcid.org/0000-0002-2197-7035"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wei Wei","raw_affiliation_strings":["National University of Singapore,School of Computing,Singapore","School of Computing, National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,School of Computing,Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100423435","display_name":"Ye Wang","orcid":"https://orcid.org/0000-0002-0123-1260"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Ye Wang","raw_affiliation_strings":["National University of Singapore,School of Computing,Singapore","Xi&#x2019;an Jiaotong University,MOE KLINNS Lab, Faculty of Electronics and Information Engineering,Xi&#x2019;an,China,710049","School of Computing, National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,School of Computing,Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Xi&#x2019;an Jiaotong University,MOE KLINNS Lab, Faculty of Electronics and Information Engineering,Xi&#x2019;an,China,710049","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8699,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.71873995,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music 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/T10863","display_name":"Voice and Speech Disorders","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9972000122070312,"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/phonation","display_name":"Phonation","score":0.9396501779556274},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6723875403404236},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6520466804504395},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6215099096298218},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48870232701301575},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47023364901542664},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.4681435227394104},{"id":"https://openalex.org/keywords/mode","display_name":"Mode (computer interface)","score":0.43106862902641296},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4135250449180603},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37790361046791077},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09965723752975464},{"id":"https://openalex.org/keywords/audiology","display_name":"Audiology","score":0.08340734243392944},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06718644499778748}],"concepts":[{"id":"https://openalex.org/C173988693","wikidata":"https://www.wikidata.org/wiki/Q678132","display_name":"Phonation","level":2,"score":0.9396501779556274},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6723875403404236},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6520466804504395},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6215099096298218},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48870232701301575},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47023364901542664},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.4681435227394104},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.43106862902641296},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4135250449180603},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37790361046791077},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09965723752975464},{"id":"https://openalex.org/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","level":1,"score":0.08340734243392944},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06718644499778748},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"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/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095669","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095669","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320311687","display_name":"Ministry of Education","ror":"https://ror.org/03m01yf64"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W276227194","https://openalex.org/W1522301498","https://openalex.org/W1987280716","https://openalex.org/W2050006267","https://openalex.org/W2067709094","https://openalex.org/W2099773255","https://openalex.org/W2143429466","https://openalex.org/W2157177661","https://openalex.org/W2408239454","https://openalex.org/W2508726376","https://openalex.org/W2579593485","https://openalex.org/W2593768305","https://openalex.org/W2885782501","https://openalex.org/W2889017834","https://openalex.org/W2935962565","https://openalex.org/W2963495494","https://openalex.org/W2963853051","https://openalex.org/W2984726089","https://openalex.org/W3008479202","https://openalex.org/W3015469592","https://openalex.org/W3035762612","https://openalex.org/W3043949498","https://openalex.org/W3165867039","https://openalex.org/W3167533889","https://openalex.org/W4295312788","https://openalex.org/W6631190155","https://openalex.org/W6731940827","https://openalex.org/W6766978945","https://openalex.org/W6911743356"],"related_works":["https://openalex.org/W1987047733","https://openalex.org/W2989774764","https://openalex.org/W2390529913","https://openalex.org/W1914697324","https://openalex.org/W2167212246","https://openalex.org/W2027982229","https://openalex.org/W3013996185","https://openalex.org/W2142368101","https://openalex.org/W4253972549","https://openalex.org/W4393733332"],"abstract_inverted_index":{"Phonation":[0],"modes":[1,18],"play":[2],"a":[3],"vital":[4],"role":[5],"in":[6],"voice":[7],"quality":[8],"evaluation":[9],"and":[10,22,57,71,82,114,134],"vocal":[11],"health":[12],"diagnosis.":[13],"Existing":[14],"studies":[15],"on":[16,102],"phonation":[17,39,49,79],"cover":[19],"feature":[20],"analysis":[21],"classification":[23],"of":[24,48,90,132,141],"vowels,":[25],"which":[26,44,85],"does":[27],"not":[28],"apply":[29],"to":[30,77],"real-life":[31],"scenarios.":[32],"In":[33],"this":[34],"paper,":[35],"we":[36,65,94],"define":[37],"the":[38,46,62,67,88,123,126,135],"mode":[40,50,80],"detection":[41],"(PMD)":[42],"problem,":[43,64],"entails":[45],"prediction":[47],"labels":[51],"as":[52,54],"well":[53],"their":[55],"onset":[56],"offset":[58],"timestamps.":[59],"To":[60],"address":[61],"PMD":[63,74],"propose":[66],"first":[68],"dataset":[69],"PMSing,":[70],"an":[72,96,103,130,139],"end-to-end":[73],"network":[75],"(P-Net)":[76],"integrate":[78],"identification":[81],"boundary":[83],"detection,":[84],"also":[86,137],"prevents":[87],"oversegmentation":[89],"frame-level":[91],"output.":[92],"Furthermore,":[93],"introduce":[95],"adapted":[97],"P-Net":[98,124],"model":[99],"(AP-Net)":[100],"based":[101],"adversarial":[104],"discriminative":[105],"training":[106],"process":[107],"using":[108],"labeled":[109],"data":[110,116],"from":[111,117],"one":[112],"singer":[113],"unlabeled":[115],"unseen":[118,144],"singers.":[119,145],"Experiments":[120],"show":[121],"that":[122],"outperforms":[125],"state-of-the-art":[127],"methods":[128],"with":[129],"F-score":[131,140],"0.680,":[133],"AP-Net":[136],"achieves":[138],"0.658":[142],"for":[143]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
