{"id":"https://openalex.org/W4416799184","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249238","title":"Synthesizing Vowel-Like Tones with Pitch Circularity","display_name":"Synthesizing Vowel-Like Tones with Pitch Circularity","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799184","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249238"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249238","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249238","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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":null,"display_name":"Kaori Hashimoto","orcid":null},"institutions":[{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kaori Hashimoto","raw_affiliation_strings":["Tokyo Metropolitan University,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Metropolitan University,Tokyo,Japan","institution_ids":["https://openalex.org/I69740276"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050509317","display_name":"Takao Kawamura","orcid":"https://orcid.org/0009-0005-3935-2809"},"institutions":[{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takao Kawamura","raw_affiliation_strings":["Tokyo Metropolitan University,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Metropolitan University,Tokyo,Japan","institution_ids":["https://openalex.org/I69740276"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056281759","display_name":"Nobutaka Ono","orcid":"https://orcid.org/0000-0003-4242-2773"},"institutions":[{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobutaka Ono","raw_affiliation_strings":["Tokyo Metropolitan University,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Metropolitan University,Tokyo,Japan","institution_ids":["https://openalex.org/I69740276"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I69740276"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32252945,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"926","last_page":"931"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.5626999735832214,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.5626999735832214,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.1784999966621399,"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":0.11649999767541885,"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/vowel","display_name":"Vowel","score":0.7541000247001648},{"id":"https://openalex.org/keywords/illusion","display_name":"Illusion","score":0.5249000191688538},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.5094000101089478},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5094000101089478},{"id":"https://openalex.org/keywords/pitch","display_name":"Pitch (Music)","score":0.4499000012874603},{"id":"https://openalex.org/keywords/fundamental-frequency","display_name":"Fundamental frequency","score":0.41359999775886536},{"id":"https://openalex.org/keywords/harmonics","display_name":"Harmonics","score":0.40529999136924744},{"id":"https://openalex.org/keywords/auditory-scene-analysis","display_name":"Auditory scene analysis","score":0.3776000142097473},{"id":"https://openalex.org/keywords/musical-tone","display_name":"Musical tone","score":0.33320000767707825}],"concepts":[{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.7541000247001648},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6636999845504761},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.5547999739646912},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5285999774932861},{"id":"https://openalex.org/C184047640","wikidata":"https://www.wikidata.org/wiki/Q182593","display_name":"Illusion","level":2,"score":0.5249000191688538},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5094000101089478},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.5094000101089478},{"id":"https://openalex.org/C153405242","wikidata":"https://www.wikidata.org/wiki/Q118819","display_name":"Pitch (Music)","level":3,"score":0.4499000012874603},{"id":"https://openalex.org/C10513763","wikidata":"https://www.wikidata.org/wiki/Q1331774","display_name":"Fundamental frequency","level":2,"score":0.41359999775886536},{"id":"https://openalex.org/C188414643","wikidata":"https://www.wikidata.org/wiki/Q3001183","display_name":"Harmonics","level":3,"score":0.40529999136924744},{"id":"https://openalex.org/C38129911","wikidata":"https://www.wikidata.org/wiki/Q4820038","display_name":"Auditory scene analysis","level":3,"score":0.3776000142097473},{"id":"https://openalex.org/C86011254","wikidata":"https://www.wikidata.org/wiki/Q2717062","display_name":"Musical tone","level":4,"score":0.33320000767707825},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.32690000534057617},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2985999882221222},{"id":"https://openalex.org/C2780583480","wikidata":"https://www.wikidata.org/wiki/Q1366327","display_name":"Tone (literature)","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C2985200191","wikidata":"https://www.wikidata.org/wiki/Q351087","display_name":"Pitch perception","level":3,"score":0.2858000099658966},{"id":"https://openalex.org/C2983311337","wikidata":"https://www.wikidata.org/wiki/Q34379","display_name":"Musical instrument","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C3020799230","wikidata":"https://www.wikidata.org/wiki/Q160289","display_name":"Auditory perception","level":3,"score":0.27950000762939453},{"id":"https://openalex.org/C184652730","wikidata":"https://www.wikidata.org/wiki/Q2357982","display_name":"Attenuation","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.2754000127315521},{"id":"https://openalex.org/C94544720","wikidata":"https://www.wikidata.org/wiki/Q2736124","display_name":"Relative pitch","level":3,"score":0.2637999951839447},{"id":"https://openalex.org/C77801330","wikidata":"https://www.wikidata.org/wiki/Q1363413","display_name":"Auditory masking","level":3,"score":0.2612999975681305},{"id":"https://openalex.org/C2777443451","wikidata":"https://www.wikidata.org/wiki/Q821413","display_name":"Auditory system","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249238","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249238","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1999417757","https://openalex.org/W2012240619","https://openalex.org/W2017697953","https://openalex.org/W2024391885","https://openalex.org/W2028549046","https://openalex.org/W2039990136","https://openalex.org/W2042442203","https://openalex.org/W2059020775","https://openalex.org/W2066684735","https://openalex.org/W2471520273","https://openalex.org/W3187128306","https://openalex.org/W4301056161"],"related_works":[],"abstract_inverted_index":{"In":[0,88],"this":[1],"paper,":[2],"we":[3,75,91,119],"present":[4],"a":[5,20,93,98],"method":[6,161,180],"for":[7],"synthesizing":[8],"vowel-like":[9],"tones":[10,24,54],"that":[11,80],"exhibit":[12],"pitch":[13,86,117,140,164],"circularity,":[14,118],"an":[15],"auditory":[16,73],"illusion":[17],"in":[18,31,70],"which":[19],"cyclic":[21],"sequence":[22],"of":[23,52,146,177],"appears":[25],"to":[26,58,77,123,128,137],"endlessly":[27],"ascend":[28],"or":[29],"descend":[30],"pitch.":[32],"Such":[33],"illusions":[34],"have":[35,60],"traditionally":[36],"been":[37,63],"achieved":[38],"using":[39],"synthetic":[40],"sinusoidal":[41],"tones,":[42],"such":[43],"as":[44],"the":[45,49,124,129,139,147,159,178],"Shepard":[46],"tone.":[47],"However,":[48],"timbral":[50],"characteristics":[51],"these":[53],"and":[55,72,85,142],"their":[56],"relationship":[57],"speech":[59],"not":[61],"yet":[62],"thoroughly":[64],"investigated.":[65],"Aiming":[66],"at":[67],"potential":[68],"applications":[69],"music":[71],"research,":[74],"attempt":[76],"synthesize":[78],"sounds":[79],"simultaneously":[81],"evoke":[82],"vowel":[83,100,143,169],"perception":[84,141],"circularity.":[87],"our":[89],"method,":[90],"construct":[92],"12":[94],"-tone":[95],"scale":[96],"from":[97],"given":[99],"by":[101],"varying":[102],"its":[103,112],"fundamental":[104],"frequency":[105],"(<tex":[106],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[107],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\mathbf{F":[108],"0}$</tex>)":[109],"while":[110,166],"preserving":[111],"spectral":[113],"envelope.":[114],"To":[115],"induce":[116],"apply":[120],"pitch-dependent":[121],"attenuation":[122],"odd":[125],"harmonics":[126],"relative":[127],"even":[130],"harmonics.":[131],"Subjective":[132],"listening":[133],"experiments":[134],"were":[135],"conducted":[136],"evaluate":[138],"identification":[144,170],"accuracy":[145,171],"synthesized":[148],"tones.":[149],"Using":[150],"five":[151],"Japanese":[152],"vowels,":[153],"\u201cA,\u201d":[154],"\u201cI,\u201d":[155],"\u201cU,\u201d":[156],"\u201cE,\u201d":[157],"\u201cO,\u201d":[158],"proposed":[160,179],"demonstrated":[162],"stronger":[163],"circularity":[165],"maintaining":[167],"high":[168],"(average":[172],"F1-score:":[173],"99.7%).":[174],"Audio":[175],"demos":[176],"are":[181],"available":[182],"online.":[183]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-11-28T00:00:00"}