{"id":"https://openalex.org/W198722553","doi":"https://doi.org/10.21437/eurospeech.1997-327","title":"Connected digit recognition in spontaneous speech","display_name":"Connected digit recognition in spontaneous speech","publication_year":1997,"publication_date":"1997-09-22","ids":{"openalex":"https://openalex.org/W198722553","doi":"https://doi.org/10.21437/eurospeech.1997-327","mag":"198722553"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.1997-327","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1997-327","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th European Conference on Speech Communication and Technology (Eurospeech 1997)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100418695","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056441019","display_name":"Etienne Bauche","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Etienne Bauche","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089528872","display_name":"Bojana Gaji\u0107","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bojana Gajic","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008413640","display_name":"Yasuhiro Minami","orcid":"https://orcid.org/0000-0003-3514-4285"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yasuhiro Minami","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109273395","display_name":"Tatsuo Matsuoka","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tatsuo Matsuoka","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5009532108","display_name":"Sadaoki Furui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sadaoki Furui","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03503805,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"923","last_page":"926"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9976999759674072,"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":0.9976999759674072,"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":0.974399983882904,"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/T12031","display_name":"Speech and dialogue systems","score":0.9298999905586243,"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/speech-recognition","display_name":"Speech recognition","score":0.8071482181549072},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6708443760871887},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6623237729072571},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5614813566207886},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.5402431488037109},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5233725309371948},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5131688714027405},{"id":"https://openalex.org/keywords/numerical-digit","display_name":"Numerical digit","score":0.5114389657974243},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.4937385022640228},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4405115842819214},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.43458572030067444},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4320411682128906},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38219571113586426},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22691547870635986},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.1325169801712036}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8071482181549072},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6708443760871887},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6623237729072571},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5614813566207886},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.5402431488037109},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5233725309371948},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5131688714027405},{"id":"https://openalex.org/C94957134","wikidata":"https://www.wikidata.org/wiki/Q82990","display_name":"Numerical digit","level":2,"score":0.5114389657974243},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.4937385022640228},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4405115842819214},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.43458572030067444},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4320411682128906},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38219571113586426},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22691547870635986},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.1325169801712036},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/eurospeech.1997-327","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1997-327","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th European Conference on Speech Communication and Technology (Eurospeech 1997)","raw_type":"proceedings-article"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:00020573","is_oa":true,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100418695","pdf_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100418695","source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai:t2r2.star.titech.ac.jp:00020573","is_oa":true,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100418695","pdf_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100418695","source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5099999904632568},{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W198722553.pdf"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W1865189210","https://openalex.org/W1920431333","https://openalex.org/W2166685558","https://openalex.org/W4239340178"],"related_works":["https://openalex.org/W2033860701","https://openalex.org/W1963930613","https://openalex.org/W1569173638","https://openalex.org/W4245698648","https://openalex.org/W2401394187","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306"],"abstract_inverted_index":{"2.":[0],"BASELINE":[1],"SYSTEM":[2],"We":[3],"performed":[4],"simple":[5,242],"speech":[6,19,40,51,74,199,219],"recognition":[7,33,129,191],"experiments":[8],"for":[9,193],"4-digit":[10],"strings":[11],"to":[12,48,94,207,212,232,240],"analyze":[13],"the":[14,50,54,78,113,116,124,139,144,155,174,209,213],"major":[15],"errors":[16],"in":[17,161,195],"spontaneous":[18],".":[20],"2.1":[21],"Recognition":[22],"system":[23,192],"\u2022Start-point":[24],"and":[25,41,64,86,128,180,220],"end-point":[26,65,140,244],"detection":[27,245],"The":[28,132,148],"input":[29,73],"of":[30,39,109,173,215,218,237],"a":[31,36,62,83,87,104,162,189,241],"realistic":[32],"system,":[34],"being":[35],"continuous":[37],"sequence":[38],"background":[42,84,221],"events,":[43],"requires":[44],"an":[45,120,233],"efficient":[46],"algorithm":[47],"distinguish":[49],"utterances":[52],"from":[53],"surrounding":[55],"background.":[56],"In":[57,184,201],"this":[58,185],"study,":[59],"we":[60,76,187,203],"implemented":[61],"start-point":[63,125],"detector":[66],"based":[67,246],"on":[68,137],"HMM":[69],"likelihoods.":[70],"For":[71],"every":[72],"frame":[75],"compared":[77,239],"probability":[79],"between":[80,115,158,226],"two":[81,159],"HMMs:":[82],"model":[85,100],"composite":[88],"all-digit":[89],"model,":[90],"whose":[91],"purpose":[92],"is":[93,126,130,134,141],"match":[95],"any":[96],"digit":[97],"event.":[98],"This":[99],"was":[101],"trained":[102],"using":[103,143,248],"large":[105],"database":[106],"containing":[107],"samples":[108],"all":[110],"digits.":[111],"When":[112],"difference":[114],"probabilities":[117],"rises":[118],"above":[119],"experimentally":[121],"determined":[122,152],"threshold,":[123],"set":[127],"started.":[131],"comparison":[133],"then":[135],"carried":[136],"until":[138],"decided,":[142],"same":[145],"likelihood-based":[146],"criterion.":[147],"thresholds":[149],"were":[150],"first":[151],"so":[153],"that":[154],"largest":[156],"pause":[157],"digits":[160],"string":[163],"did":[164],"not":[165],"exceed":[166],"320ms.":[167],"\u2022HMMs":[168],"A":[169],"feature":[170],"vector":[171,179],"consists":[172],"16-dimension":[175,181],"mean":[176],"normalized":[177],"cepstrum":[178],"delta":[182],"ABSTRACT":[183],"paper,":[186],"describe":[188],"new":[190],"4-digit-strings":[194],"Japanese":[196],"under":[197],"fluent":[198],"conditions.":[200],"particular,":[202],"introduce":[204],"several":[205],"methods":[206,230],"solve":[208],"problems":[210],"related":[211],"spontaneity":[214],"speech:":[216],"discrimination":[217],"noise,":[222],"out-ofvocabulary":[223],"words,":[224],"pauses":[225],"digits,":[227],"etc.":[228],"These":[229],"led":[231],"error":[234],"rate":[235],"reduction":[236],"76%,":[238],"startand":[243],"recognizer":[247],"non-refined":[249],"models.":[250]},"counts_by_year":[],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2025-10-10T00:00:00"}