{"id":"https://openalex.org/W2115606020","doi":"https://doi.org/10.1109/icassp.2005.1415257","title":"Mathematical Evidence of the Acoustic Universal Structure in Speech","display_name":"Mathematical Evidence of the Acoustic Universal Structure in Speech","publication_year":2006,"publication_date":"2006-10-11","ids":{"openalex":"https://openalex.org/W2115606020","doi":"https://doi.org/10.1109/icassp.2005.1415257","mag":"2115606020"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2005.1415257","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415257","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","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, Japan","Graduate school of information science and technology, University of Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Graduate school of information science and technology, University of 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":58,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"889","last_page":"892"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9948999881744385,"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":0.9821000099182129,"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/rotation","display_name":"Rotation (mathematics)","score":0.46332046389579773},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4510393440723419},{"id":"https://openalex.org/keywords/multiplicative-function","display_name":"Multiplicative function","score":0.42843982577323914},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.41580644249916077},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3940577208995819},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3868754208087921},{"id":"https://openalex.org/keywords/loudspeaker","display_name":"Loudspeaker","score":0.2778829038143158},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.22731053829193115},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.18578428030014038},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.13928911089897156},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12610992789268494}],"concepts":[{"id":"https://openalex.org/C74050887","wikidata":"https://www.wikidata.org/wiki/Q848368","display_name":"Rotation (mathematics)","level":2,"score":0.46332046389579773},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4510393440723419},{"id":"https://openalex.org/C42747912","wikidata":"https://www.wikidata.org/wiki/Q1048447","display_name":"Multiplicative function","level":2,"score":0.42843982577323914},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.41580644249916077},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3940577208995819},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3868754208087921},{"id":"https://openalex.org/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"score":0.2778829038143158},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.22731053829193115},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.18578428030014038},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.13928911089897156},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12610992789268494}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2005.1415257","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415257","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","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":11,"referenced_works":["https://openalex.org/W11805017","https://openalex.org/W112696851","https://openalex.org/W270455168","https://openalex.org/W2010800472","https://openalex.org/W2100653055","https://openalex.org/W2119419436","https://openalex.org/W2156172072","https://openalex.org/W2169878657","https://openalex.org/W6600472430","https://openalex.org/W6609945368","https://openalex.org/W6678106355"],"related_works":["https://openalex.org/W1979597421","https://openalex.org/W2007980826","https://openalex.org/W4245490552","https://openalex.org/W2061531152","https://openalex.org/W3002753104","https://openalex.org/W2077600819","https://openalex.org/W1587224694","https://openalex.org/W2042127053","https://openalex.org/W2142036596","https://openalex.org/W2072657027"],"abstract_inverted_index":{"The":[0,24,127,138],"paper":[1],"shows":[2],"mathematically":[3],"that":[4,164],"there":[5,165],"exists":[6,167],"an":[7],"acoustic":[8],"universal":[9],"structure":[10,25,97,104,140],"in":[11,40],"speech,":[12],"which":[13,36],"can":[14],"be":[15],"interpreted":[16,152],"as":[17,43,63,69,90,96,134,153],"a":[18,64,70,76,80,91,135,168,173,176],"physical":[19],"implementation":[20],"of":[21,30,45,72,79,87,99,112,157],"structural":[22],"phonology.":[23],"has":[26,141],"completely":[27],"no":[28],"dimensions":[29],"multiplicative":[31],"and":[32,56,146,155,175],"linear":[33,77,147],"transformational":[34,148],"distortions,":[35],"are":[37,150],"inevitably":[38],"involved":[39],"speech":[41,60],"communication":[42,170],"differences":[44],"vocal":[46],"tract":[47],"shape,":[48],"gender,":[49],"age,":[50],"microphone,":[51],"room,":[52],"line,":[53],"hearing":[54],"characteristics,":[55],"so":[57],"on.":[58],"A":[59,85],"event,":[61],"such":[62,89],"phone,":[65],"is":[66,93,105,132],"probabilistically":[67],"modeled":[68],"distribution":[71],"parameters":[73],"calculated":[74,133],"by":[75,108],"transformation":[78],"log":[81],"spectrum,":[82],"e.g.,":[83],"cepstrum.":[84],"set":[86],"events,":[88],"word,":[92],"relatively":[94],"captured":[95],"composed":[98],"the":[100,110,120,124,158],"distributions.":[101],"An":[102],"n-point":[103],"uniquely":[106],"determined":[107],"fixing":[109],"lengths":[111],"its":[113],"/sub":[114],"n/C/sub":[115],"2/":[116],"diagonal":[117],"lines,":[118],"namely,":[119],"distance":[121,128],"matrix":[122],"among":[123],"n":[125],"points.":[126],"between":[129,172],"two":[130],"distributions":[131],"Bhattacharyya":[136],"distance.":[137],"resulting":[139],"very":[142],"interesting":[143],"characteristics.":[144],"Multiplicative":[145],"distortions":[149],"geometrically":[151],"shift":[154],"rotation":[156],"structure,":[159],"respectively.":[160],"This":[161],"fact":[162],"implies":[163],"always":[166],"distortion-free":[169],"channel":[171],"speaker":[174],"listener.":[177]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
