{"id":"https://openalex.org/W4375869158","doi":"https://doi.org/10.1109/icassp49357.2023.10095239","title":"Representation of Vocal Tract Length Transformation Based on Group Theory","display_name":"Representation of Vocal Tract Length Transformation Based on Group Theory","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869158","doi":"https://doi.org/10.1109/icassp49357.2023.10095239"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095239","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095239","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5110466585","display_name":"Atsushi Miyashita","orcid":null},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsushi Miyashita","raw_affiliation_strings":["Nagoya University,Japan","Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Nagoya University,Japan","Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/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/T10181","display_name":"Natural Language Processing Techniques","score":0.9968000054359436,"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/vocal-tract","display_name":"Vocal tract","score":0.868060290813446},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7697110176086426},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7529115676879883},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6518274545669556},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.5321919918060303},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4899258017539978},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.48263368010520935},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.477058082818985},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4390886425971985},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4302327036857605},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.41107994318008423},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3476238548755646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3271132707595825},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.1439744234085083},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09363490343093872}],"concepts":[{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.868060290813446},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7697110176086426},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7529115676879883},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6518274545669556},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.5321919918060303},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4899258017539978},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.48263368010520935},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.477058082818985},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4390886425971985},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4302327036857605},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.41107994318008423},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3476238548755646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3271132707595825},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.1439744234085083},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09363490343093872},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095239","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095239","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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":18,"referenced_works":["https://openalex.org/W202706296","https://openalex.org/W247152494","https://openalex.org/W257179395","https://openalex.org/W2099621636","https://openalex.org/W2100118853","https://openalex.org/W2106119541","https://openalex.org/W2128413412","https://openalex.org/W2129863563","https://openalex.org/W2140567543","https://openalex.org/W2169878657","https://openalex.org/W2408610382","https://openalex.org/W2471520273","https://openalex.org/W2613752216","https://openalex.org/W3107942086","https://openalex.org/W3126776772","https://openalex.org/W3131248882","https://openalex.org/W6675409298","https://openalex.org/W6714545483"],"related_works":["https://openalex.org/W1911592522","https://openalex.org/W2087669554","https://openalex.org/W3044757496","https://openalex.org/W2994894110","https://openalex.org/W4377862891","https://openalex.org/W203970584","https://openalex.org/W2005708641","https://openalex.org/W2395719637","https://openalex.org/W2740630172","https://openalex.org/W1940093498"],"abstract_inverted_index":{"The":[0],"acoustic":[1],"characteristics":[2],"of":[3,13,49,76,116,125,146,150],"phonemes":[4],"vary":[5],"depending":[6],"on":[7,46,68,101],"the":[8,14,26,47,61,74,77,98,102,109,114,126,130,147,151],"vocal":[9,50],"tract":[10,51],"length":[11,52],"(VTL)":[12],"individual":[15],"speakers.":[16],"It":[17],"is":[18,80,85],"important":[19],"to":[20,95,112],"disentangle":[21,97],"such":[22,32],"speaker":[23,39,143,155],"information":[24,28],"from":[25],"linguistic":[27],"for":[29,122,142],"various":[30],"tasks,":[31],"as":[33],"automatic":[34],"speech":[35,63],"recognition":[36,132],"(ASR)":[37],"and":[38,59,140],"recognition.":[40],"In":[41],"this":[42,117],"paper,":[43],"we":[44,91],"focus":[45],"property":[48,115],"transformation":[53],"(VTLT)":[54],"that":[55,120],"forms":[56],"a":[57,86,93],"group,":[58],"derive":[60],"novel":[62],"representation":[64],"VTL":[65,78,99,103,127,152],"spectrum":[66,79,128,153],"based":[67],"group":[69],"theory":[70],"analysis,":[71],"where":[72],"only":[73],"phase":[75],"changed":[81],"by":[82,135],"VTLT,":[83,139],"which":[84],"simple":[87],"linear":[88],"shift.":[89],"Moreover,":[90],"propose":[92],"method":[94],"analytically":[96],"effects":[100],"spectrum.":[104],"We":[105],"conducted":[106],"experiments":[107],"with":[108],"TIMIT":[110],"dataset":[111],"clarify":[113],"feature,":[118],"demonstrationg":[119],"1)":[121],"ASR,":[123],"normalization":[124],"reduced":[129],"phoneme":[131],"error":[133],"rate":[134],"1.9":[136],"under":[137],"random":[138],"2)":[141],"recognition,":[144],"removal":[145],"amplitude":[148],"component":[149],"improved":[154],"classification":[156],"performance.":[157]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}