{"id":"https://openalex.org/W237459463","doi":"https://doi.org/10.21437/interspeech.2004-575","title":"Speech spotter: on-demand speech recognition in human-human conversation on the telephone or in face-to-face situations","display_name":"Speech spotter: on-demand speech recognition in human-human conversation on the telephone or in face-to-face situations","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W237459463","doi":"https://doi.org/10.21437/interspeech.2004-575","mag":"237459463"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-575","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-575","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"},"type":"article","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/A5030650456","display_name":"Masataka Goto","orcid":"https://orcid.org/0000-0003-1167-0977"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Masataka Goto","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Techno"],"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Techno","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024192856","display_name":"Koji Kitayama","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Koji Kitayama","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108640978","display_name":"Katsunobu Itou","orcid":null},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Katsunobu Itou","raw_affiliation_strings":["#N##TAB##TAB##TAB##TAB# Nagoya University#N##TAB##TAB##TAB#"],"affiliations":[{"raw_affiliation_string":"#N##TAB##TAB##TAB##TAB# Nagoya University#N##TAB##TAB##TAB#","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101188700","display_name":"Tetsunori Kobayashi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tetsunori Kobayashi","raw_affiliation_strings":["School of Fundamental Science and Engineering"],"affiliations":[{"raw_affiliation_string":"School of Fundamental Science and Engineering","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5030650456"],"corresponding_institution_ids":["https://openalex.org/I73613424"],"apc_list":null,"apc_paid":null,"fwci":1.3491,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.83462174,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1533","last_page":"1536"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9830999970436096,"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/T12031","display_name":"Speech and dialogue systems","score":0.9830999970436096,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9726999998092651,"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":0.955299973487854,"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/conversation","display_name":"Conversation","score":0.8482911586761475},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7698007822036743},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7576959729194641},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.6413056254386902},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5372661352157593},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.43114909529685974},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.42073673009872437},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16227641701698303},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.146908700466156},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10111081600189209}],"concepts":[{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.8482911586761475},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7698007822036743},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7576959729194641},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6413056254386902},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5372661352157593},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.43114909529685974},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.42073673009872437},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16227641701698303},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.146908700466156},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10111081600189209},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2004-575","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-575","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"}],"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/W10719946","https://openalex.org/W10968626","https://openalex.org/W12678886","https://openalex.org/W57094479","https://openalex.org/W140222416","https://openalex.org/W198720948","https://openalex.org/W1502984613","https://openalex.org/W1519655822","https://openalex.org/W2056986588","https://openalex.org/W2121715942","https://openalex.org/W2125440926"],"related_works":["https://openalex.org/W605052878","https://openalex.org/W2983519510","https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W4304187160","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W4294771049","https://openalex.org/W1523214805"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,11,48,56,71,84,87,91,96,128],"novel":[4],"speech-interface":[5],"function,":[6,112],"called":[7],"\u201cspeech":[8],"spotter\u201d,whichenablesausertoentervoicecommands":[9],"into":[10],"speech":[12,31,57,69,106],"recognizer":[13],"in":[14,33,148],"the":[15,22,100,105],"midst":[16],"of":[17,67],"natural":[18],"human-human":[19,34,125],"conversation.":[20,134],"In":[21],"past,":[23],"it":[24,37],"has":[25],"been":[26],"difficult":[27],"to":[28,41,52,145],"use":[29],"automatic":[30],"recognition":[32],"conversation":[35,126],"since":[36],"was":[38,50],"not":[39],"easy":[40],"judge,":[42],"from":[43,137],"only":[44],"microphone":[45],"input,":[46],"whether":[47],"user":[49,85],"speaking":[51],"another":[53],"person":[54],"or":[55,150],"recognizer.":[58,107],"We":[59],"solve":[60],"this":[61,110],"problem":[62],"by":[63,104],"using":[64,109,138],"two":[65,116],"kinds":[66],"nonverbal":[68],"information:":[70],"filled":[72,97],"pause":[73,98],"(a":[74],"vowel-lengthening":[75],"hesitation":[76],"like":[77],"\u201cer...\u201d)":[78],"and":[79,127],"voice":[80,88,101],"pitch.":[81],"Only":[82],"when":[83],"utters":[86],"command":[89,102],"with":[90],"high":[92],"pitch":[93],"just":[94],"after":[95],"is":[99],"accepted":[103],"By":[108],"speechspotter":[111],"we":[113],"have":[114,141],"built":[115],"application":[117],"systems:":[118],"an":[119],"ondemand":[120],"information":[121],"system":[122,130],"for":[123,131],"assisting":[124],"music-playback":[129],"enriching":[132],"telephone":[133],"The":[135],"results":[136],"these":[139],"systems":[140],"shown":[142],"thatthespeech-spotter":[143],"functionisrobustandconvenientenough":[144],"be":[146],"used":[147],"face-to-face":[149],"cellular-phone":[151],"conversations.":[152]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
