{"id":"https://openalex.org/W2990824810","doi":"https://doi.org/10.1109/taslp.2019.2955253","title":"Automatic Evaluation of Song Intelligibility Using Singing Adapted STOI and Vocal-Specific Features","display_name":"Automatic Evaluation of Song Intelligibility Using Singing Adapted STOI and Vocal-Specific Features","publication_year":2019,"publication_date":"2019-11-22","ids":{"openalex":"https://openalex.org/W2990824810","doi":"https://doi.org/10.1109/taslp.2019.2955253","mag":"2990824810"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2019.2955253","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2955253","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5067433878","display_name":"Bidisha Sharma","orcid":"https://orcid.org/0000-0002-4195-3532"},"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":"Bidisha Sharma","raw_affiliation_strings":["Electrical and Computer Engineering Department, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-4195-3532","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, 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"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ye Wang","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-0123-1260","affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":1.3088,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.81769689,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"28","issue":null,"first_page":"319","last_page":"331"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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":0.9983999729156494,"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/intelligibility","display_name":"Intelligibility (philosophy)","score":0.8389478325843811},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.7439713478088379},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.671412467956543},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.527032196521759},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3617454171180725}],"concepts":[{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.8389478325843811},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7439713478088379},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.671412467956543},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.527032196521759},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3617454171180725},{"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2019.2955253","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2955253","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W134014810","https://openalex.org/W1496771509","https://openalex.org/W1575329125","https://openalex.org/W1838578708","https://openalex.org/W1903029394","https://openalex.org/W1966264494","https://openalex.org/W1976447831","https://openalex.org/W1998946476","https://openalex.org/W1999686891","https://openalex.org/W2002485109","https://openalex.org/W2009955221","https://openalex.org/W2011007937","https://openalex.org/W2027335763","https://openalex.org/W2028339869","https://openalex.org/W2038412242","https://openalex.org/W2051104664","https://openalex.org/W2056263517","https://openalex.org/W2068810223","https://openalex.org/W2086745849","https://openalex.org/W2087297471","https://openalex.org/W2089260753","https://openalex.org/W2096927751","https://openalex.org/W2098396290","https://openalex.org/W2100971813","https://openalex.org/W2103475180","https://openalex.org/W2112844139","https://openalex.org/W2120881861","https://openalex.org/W2125114513","https://openalex.org/W2129901640","https://openalex.org/W2141998673","https://openalex.org/W2160169675","https://openalex.org/W2163536511","https://openalex.org/W2168201882","https://openalex.org/W2191779130","https://openalex.org/W2340080546","https://openalex.org/W2563477690","https://openalex.org/W2573963200","https://openalex.org/W2586352361","https://openalex.org/W2629737723","https://openalex.org/W2774707525","https://openalex.org/W2774969839","https://openalex.org/W3174435877","https://openalex.org/W4245284779","https://openalex.org/W4285719527","https://openalex.org/W4388212590","https://openalex.org/W6629589391","https://openalex.org/W6687152286","https://openalex.org/W6732186259","https://openalex.org/W6746914816","https://openalex.org/W6747108548"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390529913","https://openalex.org/W2142368101","https://openalex.org/W2372249404","https://openalex.org/W2367547137","https://openalex.org/W2354994102","https://openalex.org/W2127461790","https://openalex.org/W2069324367"],"abstract_inverted_index":{"An":[0],"objective":[1,69],"machine-driven":[2],"measure":[3,145],"of":[4,9,27,36,48,64,87,121,131,148,167,191,225],"song":[5,80,176],"intelligibility":[6,19,47,62,70,147,186,209,217],"would":[7],"be":[8],"great":[10],"utility":[11],"for":[12,61,117,135,174],"various":[13],"music":[14],"information":[15],"retrieval":[16],"tasks.":[17],"Song":[18],"mostly":[20],"depends":[21],"on":[22,165],"two":[23,42],"factors,":[24],"the":[25,34,46,52,78,88,112,127,132,136,146,149,185,192,208,223,226],"amount":[26],"interference":[28],"caused":[29],"by":[30],"background":[31],"accompaniment,":[32],"and":[33,129,157,195,215],"quality":[35],"singing":[37,90,102,109,150,159,196],"vocal.":[38,91],"We":[39,92,161,178],"leverage":[40],"these":[41,168],"factors":[43],"to":[44,72,100,144,170,183],"determine":[45],"a":[49,57,82,105,180,189,200],"song.":[50,107],"For":[51],"first":[53],"factor,":[54,138],"we":[55,139],"adapt":[56],"well":[58],"known":[59],"method":[60,99],"prediction":[63],"noisy":[65,85],"speech,":[66,122],"short":[67],"term":[68],"(STOI),":[71],"singing.":[73],"The":[74,108,205],"singing-adapted":[75],"STOI":[76],"considers":[77],"polyphonic":[79,106],"as":[81,119],"time-frequency":[83],"weighted":[84],"version":[86],"extracted":[89],"use":[93],"U-net":[94],"based":[95],"audio":[96],"source":[97],"separation":[98],"extract":[101],"vocal":[103,110],"from":[104],"shares":[111],"same":[113],"underlying":[114],"physiological":[115],"mechanism":[116],"production":[118],"that":[120],"with":[123],"some":[124],"differences":[125],"in":[126,203],"pronunciation":[128],"prosody":[130],"phonemes.":[133],"Therefore,":[134],"second":[137],"have":[140],"introduced":[141],"vocal-specific":[142,193],"features":[143,169,194],"vocal,":[151],"which":[152,221],"are":[153],"excitation":[154],"source,":[155],"spectral,":[156],"prosodic":[158],"characteristics.":[160],"perform":[162],"detailed":[163],"analysis":[164],"each":[166],"establish":[171],"their":[172],"efficacy":[173,224],"quantifying":[175],"intelligibility.":[177],"train":[179],"regression":[181],"model":[182],"derive":[184],"scores":[187],"using":[188,212],"combination":[190],"adapted":[197],"STOI,":[198],"obtaining":[199],"significant":[201],"improvement":[202],"performance.":[204],"correlation":[206],"between":[207],"score":[210,218],"obtained":[211],"proposed":[213,227],"framework":[214],"human-rated":[216],"is":[219],"0.81,":[220],"shows":[222],"approach.":[228]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}