{"id":"https://openalex.org/W297015806","doi":"https://doi.org/10.21437/interspeech.2007-325","title":"Automatic recognition of connected vowels only using speaker-invariant representation of speech dynamics","display_name":"Automatic recognition of connected vowels only using speaker-invariant representation of speech dynamics","publication_year":2007,"publication_date":"2007-08-27","ids":{"openalex":"https://openalex.org/W297015806","doi":"https://doi.org/10.21437/interspeech.2007-325","mag":"297015806"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2007-325","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-325","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Satoshi Asakawa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041213266","display_name":"Nobuaki Minematsu","orcid":"https://orcid.org/0000-0002-8778-9555"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nobuaki Minematsu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5108197272","display_name":"Keikichi Hirose","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keikichi Hirose","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"890","last_page":"893"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9994000196456909,"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":0.9951000213623047,"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":0.8005466461181641},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.668582558631897},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5992909669876099},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.5578266978263855},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5545385479927063},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5403563976287842},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.49848079681396484},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.44505465030670166},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3439410328865051},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23462066054344177},{"id":"https://openalex.org/keywords/sound-pressure","display_name":"Sound pressure","score":0.09671327471733093}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8005466461181641},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.668582558631897},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5992909669876099},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.5578266978263855},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5545385479927063},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5403563976287842},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.49848079681396484},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.44505465030670166},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3439410328865051},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23462066054344177},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.09671327471733093},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"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/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},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2007-325","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-325","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.434.5049","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.434.5049","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/~mine/paper/PDF/2007/INTERSPEECH_p890-893_t2007-8.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","score":0.49000000953674316,"display_name":"Gender equality"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1489972948","https://openalex.org/W2103632967","https://openalex.org/W2115606020","https://openalex.org/W2169878657","https://openalex.org/W3088875224"],"related_works":["https://openalex.org/W1978572805","https://openalex.org/W2383807498","https://openalex.org/W1997992934","https://openalex.org/W1987225439","https://openalex.org/W4238188170","https://openalex.org/W2125114371","https://openalex.org/W1977167953","https://openalex.org/W2556771176","https://openalex.org/W2640905660","https://openalex.org/W2402949781"],"abstract_inverted_index":{"Speech":[0],"acoustics":[1],"vary":[2],"due":[3],"to":[4,21,37,102,116],"differences":[5],"in":[6,31,104],"gender,":[7],"age,":[8],"microphone,":[9],"room,":[10],"lines,":[11],"and":[12,81,85],"a":[13,45,118],"variety":[14],"of":[15,29,41,48,120],"factors.":[16],"In":[17,107],"speech":[18,49,64,83,105],"recognition":[19],"research,":[20],"deal":[22],"with":[23],"these":[24],"inevitable":[25],"non-linguistic":[26,58],"variations,":[27],"thousands":[28],"speakers":[30],"different":[32],"acoustic":[33,39,90],"conditions":[34],"were":[35],"prepared":[36],"train":[38],"models":[40],"individual":[42],"phonemes.":[43],"Recently,":[44],"novel":[46],"representation":[47,77,113],"dynamics":[50,84],"was":[51,114],"proposed":[52],"[1,":[53],"2],":[54],"where":[55],"the":[56,111],"above":[57],"factors":[59],"are":[60,95],"effectively":[61],"removed":[62,70],"from":[63,71],"as":[65,93],"if":[66],"pitch":[67],"information":[68],"is":[69],"spectrum":[72],"by":[73],"its":[74],"smoothing.":[75],"This":[76],"captures":[78],"only":[79],"speaker-":[80],"microphone-invariant":[82],"no":[86],"absolute":[87],"or":[88],"static":[89],"properties":[91],"such":[92],"spectrums":[94],"used.":[96],"With":[97],"them,":[98],"speaker":[99],"identity":[100],"has":[101],"remain":[103],"representation.":[106],"our":[108],"previous":[109],"study,":[110],"new":[112],"applied":[115],"recognizing":[117],"sequence":[119],"isolated":[121],"vowels":[122],"[3].":[123],"The":[124]},"counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}