{"id":"https://openalex.org/W4372262998","doi":"https://doi.org/10.1109/icassp49357.2023.10097204","title":"Phoneix: Acoustic Feature Processing Strategy for Enhanced Singing Pronunciation With Phoneme Distribution Predictor","display_name":"Phoneix: Acoustic Feature Processing Strategy for Enhanced Singing Pronunciation With Phoneme Distribution Predictor","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372262998","doi":"https://doi.org/10.1109/icassp49357.2023.10097204"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10097204","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10097204","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/A5101671924","display_name":"Yuning Wu","orcid":"https://orcid.org/0000-0003-1715-2361"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuning Wu","raw_affiliation_strings":["Renmin University of China,School of Information","School of Information, Renmin University of China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China,School of Information","institution_ids":["https://openalex.org/I78988378"]},{"raw_affiliation_string":"School of Information, Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008336983","display_name":"Jiatong Shi","orcid":"https://orcid.org/0000-0002-9050-8304"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiatong Shi","raw_affiliation_strings":["Carnegie Mellon University,Language Technologies Institute","Language Technologies Institute, Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Language Technologies Institute","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tao Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Qian","raw_affiliation_strings":["Renmin University of China,School of Information","School of Information, Renmin University of China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China,School of Information","institution_ids":["https://openalex.org/I78988378"]},{"raw_affiliation_string":"School of Information, Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072814956","display_name":"Dongji Gao","orcid":"https://orcid.org/0009-0006-8885-3084"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dongji Gao","raw_affiliation_strings":["Johns Hopkins University,Center for Language and Speech Processing","Center for Language and Speech Processing, Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009985839","display_name":"Qin Jin","orcid":"https://orcid.org/0000-0001-6486-6020"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qin Jin","raw_affiliation_strings":["Renmin University of China,School of Information","School of Information, Renmin University of China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China,School of Information","institution_ids":["https://openalex.org/I78988378"]},{"raw_affiliation_string":"School of Information, Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101671924"],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04121937,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.9994999766349792,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.9561307430267334},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.8049957156181335},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7651795744895935},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7069321274757385},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6301445364952087},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5123234987258911},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4930228888988495},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3592526316642761},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.17323929071426392},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0811842679977417},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06993067264556885},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06866395473480225}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.9561307430267334},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.8049957156181335},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7651795744895935},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7069321274757385},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6301445364952087},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5123234987258911},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4930228888988495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3592526316642761},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.17323929071426392},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0811842679977417},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06993067264556885},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06866395473480225},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10097204","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10097204","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7099999785423279}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W59175527","https://openalex.org/W2030149476","https://openalex.org/W2747874407","https://openalex.org/W2889244839","https://openalex.org/W2921576841","https://openalex.org/W2937242376","https://openalex.org/W2946200149","https://openalex.org/W2962780374","https://openalex.org/W2972910332","https://openalex.org/W3015499232","https://openalex.org/W3081279708","https://openalex.org/W3082910224","https://openalex.org/W3092028330","https://openalex.org/W3097514409","https://openalex.org/W3133525064","https://openalex.org/W3158762648","https://openalex.org/W3160427568","https://openalex.org/W3163031268","https://openalex.org/W3187128306","https://openalex.org/W3190244907","https://openalex.org/W3196760057","https://openalex.org/W3207038517","https://openalex.org/W3207340675","https://openalex.org/W3212754542","https://openalex.org/W4210682690","https://openalex.org/W4221155333","https://openalex.org/W4221167708","https://openalex.org/W4224861899","https://openalex.org/W4225463329","https://openalex.org/W4280572880","https://openalex.org/W4296068763","https://openalex.org/W4297841449","https://openalex.org/W4298397573","https://openalex.org/W4312625753","https://openalex.org/W6761725420","https://openalex.org/W6763832098","https://openalex.org/W6783382068","https://openalex.org/W6783867762","https://openalex.org/W6809623261"],"related_works":["https://openalex.org/W2390529913","https://openalex.org/W2142368101","https://openalex.org/W2372249404","https://openalex.org/W2367547137","https://openalex.org/W2354994102","https://openalex.org/W2387733758","https://openalex.org/W2376664795","https://openalex.org/W2366077683","https://openalex.org/W2374220079","https://openalex.org/W2377483540"],"abstract_inverted_index":{"Singing":[0],"voice":[1,13],"synthesis":[2],"(SVS),":[3],"as":[4],"a":[5,15,75],"specific":[6],"task":[7],"for":[8],"generating":[9],"the":[10,27,30,38,44,53,56,81,84,88,106],"vocal":[11],"singing":[12,31,89],"from":[14],"music":[16,40,57,85],"score,":[17],"has":[18,32],"drawn":[19],"much":[20],"attention":[21],"in":[22,96,102,111],"recent":[23],"years.":[24],"SVS":[25,48,98],"faces":[26],"challenge":[28],"that":[29],"various":[33,103],"pronunciation":[34],"flexibility":[35],"conditioned":[36],"on":[37],"same":[39],"score.":[41],"Most":[42],"of":[43,47,108],"previous":[45],"works":[46],"can":[49,92],"not":[50],"well":[51],"handle":[52],"misalignment":[54],"between":[55,83],"score":[58,86],"and":[59,87,114],"actual":[60],"singing.":[61],"In":[62],"this":[63],"paper,":[64],"we":[65],"propose":[66],"an":[67],"acoustic":[68],"feature":[69],"processing":[70],"strategy,":[71],"named":[72],"PHONEix,":[73],"with":[74],"phoneme":[76],"distribution":[77],"predictor,":[78],"to":[79],"alleviate":[80],"gap":[82],"voice,":[90],"which":[91],"be":[93],"easily":[94],"adopted":[95],"different":[97],"systems.":[99],"Extensive":[100],"experiments":[101],"settings":[104],"demonstrate":[105],"effectiveness":[107],"our":[109],"PHONEix":[110],"both":[112],"objective":[113],"subjective":[115],"evaluations.":[116]},"counts_by_year":[],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}
