{"id":"https://openalex.org/W2168862296","doi":"https://doi.org/10.1109/icassp.2008.4518555","title":"Multi-stream parameterization for structural speech recognition","display_name":"Multi-stream parameterization for structural speech recognition","publication_year":2008,"publication_date":"2008-03-01","ids":{"openalex":"https://openalex.org/W2168862296","doi":"https://doi.org/10.1109/icassp.2008.4518555","mag":"2168862296"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2008.4518555","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518555","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 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/A5103581782","display_name":"Satoshi Asakawa","orcid":null},"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":false,"raw_author_name":"Satoshi Asakawa","raw_affiliation_strings":["Graduate School of Frontier Sciences, University of Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Frontier Sciences, University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","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":false,"raw_author_name":"Nobuaki Minematsu","raw_affiliation_strings":["Graduate School of Frontier Sciences, University of Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Frontier Sciences, University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108197272","display_name":"Keikichi Hirose","orcid":null},"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":false,"raw_author_name":"Keikichi Hirose","raw_affiliation_strings":["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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4097","last_page":"4100"},"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":0.9998999834060669,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7770717740058899},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.745132565498352},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6396193504333496},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5536103844642639},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4154647886753082},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.408645898103714},{"id":"https://openalex.org/keywords/sound-pressure","display_name":"Sound pressure","score":0.054819703102111816}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7770717740058899},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.745132565498352},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6396193504333496},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5536103844642639},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4154647886753082},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.408645898103714},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.054819703102111816},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2008.4518555","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518555","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W46300955","https://openalex.org/W297015806","https://openalex.org/W1489972948","https://openalex.org/W1974736851","https://openalex.org/W2103632967","https://openalex.org/W2111148778","https://openalex.org/W2115606020","https://openalex.org/W2134061030","https://openalex.org/W2156172072","https://openalex.org/W2169878657","https://openalex.org/W2314297151","https://openalex.org/W2402172738","https://openalex.org/W3088875224","https://openalex.org/W6601913465","https://openalex.org/W6610627759","https://openalex.org/W6629462044","https://openalex.org/W6783348338"],"related_works":["https://openalex.org/W2357191878","https://openalex.org/W1997078944","https://openalex.org/W1968065688","https://openalex.org/W2142945567","https://openalex.org/W1552846815","https://openalex.org/W2030332364","https://openalex.org/W4221144054","https://openalex.org/W2005459225","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"Recently,":[0],"a":[1,61,72,110],"novel":[2],"and":[3,32,38],"structural":[4,27,68,123],"representation":[5,28,56],"of":[6,63,90,102,121,141],"speech":[7,34],"was":[8,57],"proposed":[9,116,127],"[1,":[10],"2],":[11],"where":[12],"the":[13,54,76,88,96,107,119,122,135,142],"inevitable":[14],"acoustic":[15,44],"variations":[16],"caused":[17],"by":[18],"nonlinguistic":[19],"factors":[20],"are":[21],"effectively":[22],"removed":[23],"from":[24],"speech.":[25,92],"This":[26],"captures":[29],"only":[30,129],"microphone-":[31],"speaker-invariant":[33],"contrasts":[35],"or":[36,42],"dynamics":[37],"uses":[39],"no":[40],"absolute":[41],"static":[43],"properties":[45],"directly":[46],"such":[47],"as":[48],"spectrums.":[49],"In":[50,106],"our":[51],"previous":[52],"study,":[53],"new":[55,97],"applied":[58,95],"to":[59,99,117,139],"recognizing":[60,100],"sequence":[62],"isolated":[64],"vowels":[65,104],"[3].":[66],"The":[67,126],"models":[69,98],"trained":[70,79],"with":[71,80,130],"single":[73],"speaker":[74],"outperformed":[75],"conventional":[77,143],"HMMs":[78],"more":[81],"than":[82],"four":[83],"thousand":[84],"speakers":[85,133],"even":[86],"in":[87],"case":[89],"noisy":[91],"We":[93],"also":[94],"utterances":[101],"connected":[103],"[4].":[105],"current":[108],"paper,":[109],"multiple":[111],"stream":[112],"structuralization":[113],"method":[114,128],"is":[115],"improve":[118],"performance":[120,138],"recognition":[124],"framework.":[125],"8":[131],"training":[132],"shows":[134],"very":[136],"comparable":[137],"that":[140],"4,130-speaker":[144],"triphone-based":[145],"HMMs.":[146]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}