{"id":"https://openalex.org/W2130901403","doi":"https://doi.org/10.1109/iscslp.2010.5684843","title":"Aligning singing voice with MIDI melody using synthesized audio signal","display_name":"Aligning singing voice with MIDI melody using synthesized audio signal","publication_year":2010,"publication_date":"2010-11-01","ids":{"openalex":"https://openalex.org/W2130901403","doi":"https://doi.org/10.1109/iscslp.2010.5684843","mag":"2130901403"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2010.5684843","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2010.5684843","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 7th International Symposium on Chinese Spoken Language Processing","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/A5021872761","display_name":"Minghui Dong","orcid":"https://orcid.org/0000-0001-6543-2929"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Minghui Dong","raw_affiliation_strings":["Human Language Technology Department, Institute of Infocomm Research, Agency for Science, Technology and Research, Singapore","Human Language Technology Department, Institute for Infocomm Research, A*Star, 1 Fusionopolis Way, #21-01 Connexis, Singapore 138632"],"affiliations":[{"raw_affiliation_string":"Human Language Technology Department, Institute of Infocomm Research, Agency for Science, Technology and Research, Singapore","institution_ids":["https://openalex.org/I115228651"]},{"raw_affiliation_string":"Human Language Technology Department, Institute for Infocomm Research, A*Star, 1 Fusionopolis Way, #21-01 Connexis, Singapore 138632","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059762329","display_name":"Paul Chan","orcid":"https://orcid.org/0000-0002-5604-4905"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Paul Chan","raw_affiliation_strings":["Human Language Technology Department, Institute of Infocomm Research, Agency for Science, Technology and Research, Singapore","Human Language Technology Department, Institute for Infocomm Research, A*Star, 1 Fusionopolis Way, #21-01 Connexis, Singapore 138632"],"affiliations":[{"raw_affiliation_string":"Human Language Technology Department, Institute of Infocomm Research, Agency for Science, Technology and Research, Singapore","institution_ids":["https://openalex.org/I115228651"]},{"raw_affiliation_string":"Human Language Technology Department, Institute for Infocomm Research, A*Star, 1 Fusionopolis Way, #21-01 Connexis, Singapore 138632","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108056229","display_name":"Ling Cen","orcid":"https://orcid.org/0000-0002-1674-1052"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ling Cen","raw_affiliation_strings":["Human Language Technology Department, Institute of Infocomm Research, Agency for Science, Technology and Research, Singapore","Human Language Technology Department, Institute for Infocomm Research, A*Star, 1 Fusionopolis Way, #21-01 Connexis, Singapore 138632"],"affiliations":[{"raw_affiliation_string":"Human Language Technology Department, Institute of Infocomm Research, Agency for Science, Technology and Research, Singapore","institution_ids":["https://openalex.org/I115228651"]},{"raw_affiliation_string":"Human Language Technology Department, Institute for Infocomm Research, A*Star, 1 Fusionopolis Way, #21-01 Connexis, Singapore 138632","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Human Language Technology Department, Institute of Infocomm Research, Agency for Science, Technology and Research, Singapore","Human Language Technology Department, Institute for Infocomm Research, A*Star, 1 Fusionopolis Way, #21-01 Connexis, Singapore 138632"],"affiliations":[{"raw_affiliation_string":"Human Language Technology Department, Institute of Infocomm Research, Agency for Science, Technology and Research, Singapore","institution_ids":["https://openalex.org/I115228651"]},{"raw_affiliation_string":"Human Language Technology Department, Institute for Infocomm Research, A*Star, 1 Fusionopolis Way, #21-01 Connexis, Singapore 138632","institution_ids":["https://openalex.org/I3005327000"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5021872761"],"corresponding_institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.19055955,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"95","last_page":"98"},"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/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":0.987500011920929,"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/midi","display_name":"MIDI","score":0.9799740314483643},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.9369040727615356},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7427752017974854},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7331364154815674},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.521393358707428},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4932546019554138},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4881313741207123},{"id":"https://openalex.org/keywords/musical-notation","display_name":"Musical notation","score":0.4312194883823395},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.41069096326828003},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.2852916717529297},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2031461000442505},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.09559890627861023}],"concepts":[{"id":"https://openalex.org/C8112396","wikidata":"https://www.wikidata.org/wiki/Q80535","display_name":"MIDI","level":2,"score":0.9799740314483643},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.9369040727615356},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7427752017974854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7331364154815674},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.521393358707428},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4932546019554138},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4881313741207123},{"id":"https://openalex.org/C88639978","wikidata":"https://www.wikidata.org/wiki/Q233861","display_name":"Musical notation","level":3,"score":0.4312194883823395},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.41069096326828003},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.2852916717529297},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2031461000442505},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.09559890627861023},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2010.5684843","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2010.5684843","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 7th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W106639881","https://openalex.org/W127994334","https://openalex.org/W1545600033","https://openalex.org/W1797486849","https://openalex.org/W2007431733","https://openalex.org/W2030511115","https://openalex.org/W2124762682","https://openalex.org/W2125935583","https://openalex.org/W2127265017","https://openalex.org/W2128160875","https://openalex.org/W2152205330","https://openalex.org/W2153331925","https://openalex.org/W2275238206","https://openalex.org/W6604351559","https://openalex.org/W6605238236","https://openalex.org/W6632733265","https://openalex.org/W6678722470","https://openalex.org/W6679084306","https://openalex.org/W6682222477","https://openalex.org/W6694178644"],"related_works":["https://openalex.org/W2002473771","https://openalex.org/W2203718630","https://openalex.org/W1907897748","https://openalex.org/W1515198570","https://openalex.org/W2245965895","https://openalex.org/W4234749112","https://openalex.org/W2121148209","https://openalex.org/W1575424942","https://openalex.org/W2398454874","https://openalex.org/W2418422832"],"abstract_inverted_index":{"Proper":[0],"alignment":[1,69,79],"of":[2],"singing":[3,14,29,53],"voice":[4,15,30,54],"to":[5,27,66],"its":[6,32],"corresponding":[7],"musical":[8],"score":[9],"is":[10,37,64,81],"particularly":[11],"important":[12],"for":[13,51],"analysis":[16],"and":[17,55],"processing":[18],"in":[19],"many":[20],"applications.":[21],"This":[22],"paper":[23],"proposes":[24],"a":[25,41],"method":[26,63],"align":[28],"with":[31],"MIDI":[33,36,56],"melody.":[34],"The":[35],"first":[38],"converted":[39],"into":[40],"synthesized":[42],"music":[43],"audio":[44],"file.":[45],"Then":[46],"spectral":[47],"features":[48],"are":[49],"calculated":[50],"both":[52],"synthesis":[57],"files.":[58],"Next":[59],"dynamic":[60],"time":[61],"warping":[62],"used":[65],"perform":[67],"forced":[68],"between":[70],"the":[71,78],"two":[72],"feature":[73],"sequences.":[74],"Experiments":[75],"show":[76],"that":[77],"result":[80],"promising.":[82]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}