{"id":"https://openalex.org/W2921017930","doi":"https://doi.org/10.23919/apsipa.2018.8659615","title":"Analysis of Speech and Singing Signals for Temporal Alignment","display_name":"Analysis of Speech and Singing Signals for Temporal Alignment","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2921017930","doi":"https://doi.org/10.23919/apsipa.2018.8659615","mag":"2921017930"},"language":"en","primary_location":{"id":"doi:10.23919/apsipa.2018.8659615","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659615","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5016027101","display_name":"Karthika Vijayan","orcid":"https://orcid.org/0000-0001-7281-1329"},"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":true,"raw_author_name":"Karthika Vijayan","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101856962","display_name":"Xiaoxue Gao","orcid":"https://orcid.org/0000-0003-1920-5228"},"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":"Xiaoxue Gao","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"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/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":"Haizhou Li","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5016027101"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":1.8166,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.86819598,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1893","last_page":"1898"},"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":0.9997000098228455,"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":0.9987999796867371,"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":0.9288761615753174},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7850217223167419},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7296475172042847},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.6636265516281128},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.6604553461074829},{"id":"https://openalex.org/keywords/lyrics","display_name":"Lyrics","score":0.6289777755737305},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49048444628715515},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4694231152534485},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4613921642303467},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4448261857032776},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.43116194009780884},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3497140407562256},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3401428461074829},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.26603782176971436},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.1027381420135498},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08168947696685791}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.9288761615753174},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7850217223167419},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7296475172042847},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.6636265516281128},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.6604553461074829},{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.6289777755737305},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49048444628715515},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4694231152534485},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4613921642303467},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4448261857032776},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.43116194009780884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3497140407562256},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3401428461074829},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.26603782176971436},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.1027381420135498},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08168947696685791},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/apsipa.2018.8659615","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659615","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":37,"referenced_works":["https://openalex.org/W31703023","https://openalex.org/W1508848762","https://openalex.org/W1632690104","https://openalex.org/W1665484889","https://openalex.org/W1875892135","https://openalex.org/W1904711963","https://openalex.org/W2028272688","https://openalex.org/W2030351702","https://openalex.org/W2060998236","https://openalex.org/W2067709094","https://openalex.org/W2088867696","https://openalex.org/W2097645910","https://openalex.org/W2102870814","https://openalex.org/W2108382268","https://openalex.org/W2112844139","https://openalex.org/W2128123288","https://openalex.org/W2130901403","https://openalex.org/W2134387846","https://openalex.org/W2150933458","https://openalex.org/W2156230116","https://openalex.org/W2166472876","https://openalex.org/W2269051851","https://openalex.org/W2294038178","https://openalex.org/W2318584973","https://openalex.org/W2408190184","https://openalex.org/W2482558056","https://openalex.org/W2606502962","https://openalex.org/W2785608393","https://openalex.org/W2786495826","https://openalex.org/W3094114204","https://openalex.org/W3142619648","https://openalex.org/W4211139177","https://openalex.org/W6601272821","https://openalex.org/W6630532172","https://openalex.org/W6639128508","https://openalex.org/W6697024540","https://openalex.org/W6736711317"],"related_works":["https://openalex.org/W2025848302","https://openalex.org/W1975454382","https://openalex.org/W2799441357","https://openalex.org/W5449343","https://openalex.org/W2409530148","https://openalex.org/W2053642297","https://openalex.org/W4250508028","https://openalex.org/W2070513494","https://openalex.org/W1974071677","https://openalex.org/W1840351222"],"abstract_inverted_index":{"Accurate":[0],"alignment":[1,34],"between":[2,35,114],"singing":[3,17,27,50,80,90,117],"signal":[4,18],"and":[5,26,49,79,89,116,131,140],"its":[6],"spoken":[7],"lyrics":[8],"at":[9],"frame-level":[10],"is":[11,37],"imperative":[12],"to":[13,52,57,153],"several":[14],"applications":[15],"in":[16,70,124,132,157],"processing.":[19],"As":[20],"the":[21,32,45,65,84,146,154],"acoustic":[22],"characteristics":[23,46,66,112],"of":[24,47,67,105],"speech":[25,48,115],"signals":[28,51,91],"differ":[29],"significantly,":[30],"finding":[31],"temporal":[33,59,129,158],"them":[36],"not":[38],"easy.":[39],"In":[40,137],"this":[41],"paper,":[42],"we":[43,101,143],"study":[44],"identify":[53],"their":[54],"common":[55],"properties":[56],"facilitate":[58],"alignment.":[60,159],"We":[61],"observe":[62],"that:":[63],"(i)":[64],"excitation":[68],"source":[69],"human":[71],"voice":[72],"production":[73],"mechanism":[74],"largely":[75],"vary":[76],"with":[77],"speaking":[78,88],"and,":[81],"(ii)":[82],"for":[83,128],"same":[85],"linguistic":[86],"content,":[87],"present":[92],"very":[93],"different":[94],"formant":[95],"patterns.":[96],"Based":[97],"on":[98],"these":[99],"observations,":[100],"formulate":[102],"a":[103,133],"set":[104],"tandem":[106,120,148],"features":[107,121,149,156],"that":[108,145],"represent":[109],"only":[110],"those":[111],"consistent":[113],"signals.":[118],"Such":[119],"are":[122,150],"used":[123],"dynamic":[125],"time":[126],"warping":[127],"alignment,":[130],"speech-to-singing":[134],"conversion":[135],"experiment.":[136],"both":[138],"objective":[139],"subjective":[141],"evaluations,":[142],"show":[144],"proposed":[147],"significantly":[151],"superior":[152],"baseline":[155]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}