{"id":"https://openalex.org/W3012546161","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023119","title":"Disfluency Detection Based on Speech-Aware Token-by-Token Sequence Labeling with BLSTM-CRFs and Attention Mechanisms","display_name":"Disfluency Detection Based on Speech-Aware Token-by-Token Sequence Labeling with BLSTM-CRFs and Attention Mechanisms","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3012546161","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023119","mag":"3012546161"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc47483.2019.9023119","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5009756622","display_name":"Tomohiro Tanaka","orcid":"https://orcid.org/0000-0001-7442-4912"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Tomohiro Tanaka","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060644399","display_name":"Ryo Masumura","orcid":"https://orcid.org/0000-0002-2415-4149"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryo Masumura","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087290011","display_name":"Takafumi Moriya","orcid":"https://orcid.org/0000-0003-1942-7250"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takafumi Moriya","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109336432","display_name":"Takanobu Oba","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takanobu Oba","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067237053","display_name":"Yushi Aono","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yushi Aono","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5009756622"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":0.8401,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.8125105,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"abs 1508 1991","issue":null,"first_page":"1009","last_page":"1013"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9958000183105469,"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":0.9947999715805054,"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/crfs","display_name":"CRFS","score":0.9344226121902466},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.8391163349151611},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7545599937438965},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.6176196336746216},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5476816892623901},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5273236632347107},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.36104241013526917},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.31277164816856384},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.19261866807937622},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.061044842004776},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.052574992179870605}],"concepts":[{"id":"https://openalex.org/C2775953691","wikidata":"https://www.wikidata.org/wiki/Q5013874","display_name":"CRFS","level":3,"score":0.9344226121902466},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.8391163349151611},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7545599937438965},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.6176196336746216},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5476816892623901},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5273236632347107},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.36104241013526917},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31277164816856384},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.19261866807937622},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.061044842004776},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.052574992179870605},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc47483.2019.9023119","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4099999964237213,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W854541894","https://openalex.org/W1940872118","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2161274063","https://openalex.org/W2293765256","https://openalex.org/W2406344726","https://openalex.org/W2705373224","https://openalex.org/W2756923881","https://openalex.org/W2889477554","https://openalex.org/W2963625095","https://openalex.org/W2963729456","https://openalex.org/W3201888710","https://openalex.org/W6623517193","https://openalex.org/W6640362995","https://openalex.org/W6679436768","https://openalex.org/W6713880093","https://openalex.org/W6802169743"],"related_works":["https://openalex.org/W2962906565","https://openalex.org/W2798423868","https://openalex.org/W3015678144","https://openalex.org/W2076440176","https://openalex.org/W2061027419","https://openalex.org/W2140585957","https://openalex.org/W2054134081","https://openalex.org/W1675450783","https://openalex.org/W189110383","https://openalex.org/W2404235285"],"abstract_inverted_index":{"This":[0,97],"paper":[1],"presents":[2],"a":[3,46,51,112,139],"new":[4],"method":[5,113,140,178],"for":[6,114,141],"token-by-token":[7,47,115],"sequence":[8,48,116,143],"labeling":[9,49,144,186],"that":[10,78,119,175,190],"can":[11,120],"leverage":[12],"not":[13,65],"only":[14],"lexical":[15,61,94,123,192],"information":[16,20,62,95,101,126],"but":[17],"also":[18],"speech":[19,56,73,80,92,100,125,169],"without":[21,127],"any":[22,129],"alignments.":[23,130],"Our":[24,171],"motivation":[25],"is":[26,42,64,77],"to":[27,72,86,102,162],"detect":[28],"disfluencies":[29,69,167],"such":[30],"as":[31,45],"fillers":[32],"and":[33,81,93,124,181],"word":[34],"fragments":[35],"robustly":[36],"from":[37,168],"spontaneous":[38],"speech.":[39],"Disfluency":[40],"detection":[41],"often":[43],"modeled":[44],"using":[50,179,191],"transcribed":[52,83],"text":[53,84],"via":[54],"automatic":[55],"recognition.":[57],"However,":[58],"utilizing":[59],"the":[60,68,79,82,103,164,176,185],"alone":[63],"sufficient":[66],"because":[67],"cause":[70],"changes":[71],"information.":[74],"One":[75],"problem":[76],"need":[85],"be":[87],"aligned":[88],"when":[89],"we":[90,110,134],"handle":[91],"simultaneously.":[96],"prevents":[98],"introducing":[99],"disfluency":[104],"detection.":[105],"To":[106,131],"solve":[107],"this":[108,132],"problem,":[109],"propose":[111],"labeling,":[117],"one":[118],"simultaneously":[121],"use":[122],"requiring":[128],"end,":[133],"introduce":[135],"attention":[136,158],"mechanisms":[137,159],"into":[138],"neural":[142,152],"based":[145],"on":[146],"bi-directional":[147],"long":[148],"short-term":[149],"memory":[150],"recurrent":[151],"network":[153],"conditional":[154],"random":[155],"fields.":[156],"The":[157],"enable":[160],"us":[161],"find":[163],"term":[165],"of":[166],"automatically.":[170],"experimental":[172],"results":[173],"show":[174],"proposed":[177],"acoustic":[180],"prosodic":[182],"features":[183,193],"improves":[184],"accuracy":[187],"compared":[188],"with":[189],"alone.":[194]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}