{"id":"https://openalex.org/W2405834540","doi":"https://doi.org/10.1109/icassp.2016.7471679","title":"Speech analysis of sung-speech and lyric recognition in monophonic singing","display_name":"Speech analysis of sung-speech and lyric recognition in monophonic singing","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2405834540","doi":"https://doi.org/10.1109/icassp.2016.7471679","mag":"2405834540"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7471679","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7471679","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 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/A5057147081","display_name":"Dairoku Kawai","orcid":null},"institutions":[{"id":"https://openalex.org/I136259955","display_name":"Toyohashi University of Technology","ror":"https://ror.org/04ezg6d83","country_code":"JP","type":"education","lineage":["https://openalex.org/I136259955"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Dairoku Kawai","raw_affiliation_strings":["Department of Computer Science and Engineering, Toyohashi University of Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Toyohashi University of Technology, Japan","institution_ids":["https://openalex.org/I136259955"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109057821","display_name":"Kazumasa Yamamoto","orcid":"https://orcid.org/0009-0005-4085-0741"},"institutions":[{"id":"https://openalex.org/I136259955","display_name":"Toyohashi University of Technology","ror":"https://ror.org/04ezg6d83","country_code":"JP","type":"education","lineage":["https://openalex.org/I136259955"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazumasa Yamamoto","raw_affiliation_strings":["Department of Computer Science and Engineering, Toyohashi University of Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Toyohashi University of Technology, Japan","institution_ids":["https://openalex.org/I136259955"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018428974","display_name":"Seiichi Nakagawa","orcid":"https://orcid.org/0000-0002-6533-5536"},"institutions":[{"id":"https://openalex.org/I136259955","display_name":"Toyohashi University of Technology","ror":"https://ror.org/04ezg6d83","country_code":"JP","type":"education","lineage":["https://openalex.org/I136259955"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Seiichi Nakagawa","raw_affiliation_strings":["Department of Computer Science and Engineering, Toyohashi University of Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Toyohashi University of Technology, Japan","institution_ids":["https://openalex.org/I136259955"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7658,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.7093521,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"105","issue":null,"first_page":"271","last_page":"275"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994999766349792,"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/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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":0.8910079002380371},{"id":"https://openalex.org/keywords/lyrics","display_name":"Lyrics","score":0.8452601432800293},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8133995532989502},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6380215883255005},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.577078104019165},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5715125203132629},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.5124655365943909},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2859588861465454},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2310624122619629}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8910079002380371},{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.8452601432800293},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8133995532989502},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6380215883255005},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.577078104019165},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5715125203132629},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.5124655365943909},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2859588861465454},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2310624122619629},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7471679","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7471679","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W37526647","https://openalex.org/W112239495","https://openalex.org/W178884067","https://openalex.org/W218087806","https://openalex.org/W1519655822","https://openalex.org/W1521340514","https://openalex.org/W1992196410","https://openalex.org/W2052675777","https://openalex.org/W2057745663","https://openalex.org/W2059239154","https://openalex.org/W2089204011","https://openalex.org/W2127615536","https://openalex.org/W2139878068","https://openalex.org/W2164282073","https://openalex.org/W2226734577","https://openalex.org/W2537965973","https://openalex.org/W4235128394","https://openalex.org/W6601563604","https://openalex.org/W6604617924","https://openalex.org/W6607294247","https://openalex.org/W6631117800","https://openalex.org/W6631254342","https://openalex.org/W6689048222"],"related_works":["https://openalex.org/W2360952181","https://openalex.org/W4310670065","https://openalex.org/W634160686","https://openalex.org/W2597614303","https://openalex.org/W3214861561","https://openalex.org/W2389838651","https://openalex.org/W2378183644","https://openalex.org/W2374220079","https://openalex.org/W2377483540","https://openalex.org/W2287414930"],"abstract_inverted_index":{"Lyric":[0],"recognition":[1,49,59,106],"in":[2,60,107],"singing":[3,16,62,70],"is":[4],"challenging":[5],"because":[6],"of":[7,10,15,26,32],"a":[8,13,79,101],"number":[9],"problems,":[11],"including":[12],"lack":[14],"databases,":[17],"superposed":[18],"musical":[19,66],"instruments":[20],"and":[21,40,43,85,95],"different":[22],"spectral":[23,33],"variations.":[24],"First":[25],"all,":[27],"we":[28,44,55,72],"investigated":[29],"the":[30,51,110],"difference":[31],"variations":[34],"among":[35],"read":[36],"speech,":[37],"spontaneous":[38,114],"speech":[39,42,48,115],"sung":[41,47],"found":[45],"that":[46,63],"was":[50],"most":[52],"difficult.":[53],"Next,":[54],"consider":[56],"Japanese":[57],"lyric":[58,105],"monophonic":[61],"contains":[64],"no":[65],"instruments.":[67],"To":[68],"express":[69],"well,":[71],"use":[73],"an":[74],"n-gram":[75],"language":[76],"model":[77],"with":[78,109],"lyrics":[80],"corpus,":[81],"singing-adapted":[82],"acoustic":[83,97],"models,":[84],"plural":[86],"pronunciation":[87],"lexicons":[88],"for":[89,113],"vowel-lengthening.":[90],"We":[91,99],"also":[92],"compare":[93],"GMM-HMM":[94],"DNN-HMM":[96],"models.":[98],"obtained":[100],"remarkable":[102],"improvement":[103],"on":[104],"comparison":[108],"baseline":[111],"system":[112],"recognition.":[116]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}