{"id":"https://openalex.org/W2156172072","doi":"https://doi.org/10.1109/icassp.2004.1326053","title":"Yet another acoustic representation of speech sounds","display_name":"Yet another acoustic representation of speech sounds","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2156172072","doi":"https://doi.org/10.1109/icassp.2004.1326053","mag":"2156172072"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1326053","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","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/A5041213266","display_name":"Nobuaki Minematsu","orcid":"https://orcid.org/0000-0002-8778-9555"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"N. Minematsu","raw_affiliation_strings":["Graduate School of Information Science and Technology, University of Tokyo, Bunkyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, University of Tokyo, Bunkyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5041213266"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"585"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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/speech-recognition","display_name":"Speech recognition","score":0.7308051586151123},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.715429425239563},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6941194534301758},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.5263166427612305},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.5014042854309082},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.48146548867225647},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.47114935517311096},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.47075536847114563},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.4564327299594879},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4456588923931122},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4262723922729492},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.34039247035980225},{"id":"https://openalex.org/keywords/sound-pressure","display_name":"Sound pressure","score":0.09635493159294128}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7308051586151123},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.715429425239563},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6941194534301758},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.5263166427612305},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.5014042854309082},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.48146548867225647},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.47114935517311096},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.47075536847114563},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.4564327299594879},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4456588923931122},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4262723922729492},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.34039247035980225},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.09635493159294128},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2004.1326053","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.799.9757","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.799.9757","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.gavo.t.u-tokyo.ac.jp/%7Emine/paper/PDF/2004/ICASSP_p585-588_t2004-5.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W112696851","https://openalex.org/W1591172823","https://openalex.org/W2010800472","https://openalex.org/W2086705963","https://openalex.org/W2119419436","https://openalex.org/W2146871184","https://openalex.org/W2169878657","https://openalex.org/W2405879112","https://openalex.org/W6635376843","https://openalex.org/W6672311292","https://openalex.org/W6678106355"],"related_works":["https://openalex.org/W1546240199","https://openalex.org/W2069501481","https://openalex.org/W2400533375","https://openalex.org/W1840351222","https://openalex.org/W2470236000","https://openalex.org/W2097143083","https://openalex.org/W2063862874","https://openalex.org/W2154415461","https://openalex.org/W1923241916","https://openalex.org/W642007152"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"yet":[3],"another":[4],"representation":[5],"of":[6,85,99,133,141],"speech":[7,11,22,27],"sounds.":[8],"The":[9,65],"proposed":[10,114],"modeling":[12],"can":[13],"remove":[14],"both":[15],"multiplicative":[16],"and":[17,45,62,128],"linear":[18],"transformational":[19],"distortion":[20,37],"from":[21],"theoretically.":[23],"It":[24],"means":[25],"that":[26],"sounds":[28],"are":[29],"represented":[30],"without":[31,137],"being":[32],"affected":[33],"by":[34],"any":[35],"static":[36],"inevitably":[38],"involved":[39],"in":[40,51,81,146],"production,":[41],"encoding,":[42],"transmission,":[43],"decoding,":[44],"hearing":[46],"processes,":[47],"such":[48],"as":[49],"differences":[50],"vocal":[52],"tract":[53],"length,":[54],"gender,":[55],"age,":[56],"microphone,":[57],"room,":[58],"line,":[59],"auditory":[60],"characteristics,":[61],"so":[63],"on.":[64],"method":[66,91,115],"acoustically":[67],"models":[68,140],"not":[69],"individual":[70,143],"phones":[71,86,144],"but":[72],"their":[73],"entire":[74],"system,":[75],"where":[76,130],"only":[77],"acoustic":[78,97,139],"interrelation":[79],"embedded":[80],"all":[82],"the":[83,90,111,113,131,142,147],"kinds":[84],"is":[87,116,135],"focused.":[88],"Since":[89],"provides":[92],"us":[93],"with":[94],"no":[95],"absolute":[96],"properties":[98],"phones,":[100],"it":[101],"cannot":[102],"recognize":[103],"or":[104],"synthesize":[105],"even":[106],"a":[107],"single":[108],"phone.":[109],"On":[110],"contrary,":[112],"shown":[117],"to":[118,121,124],"be":[119,122],"able":[120],"applied":[123],"pronunciation":[125,134],"assessment":[126],"effectively":[127],"reliably,":[129],"proficiency":[132],"estimated":[136],"using":[138],"directly":[145],"matching.":[148]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}