{"id":"https://openalex.org/W3011644728","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023288","title":"Classification of causes of speech recognition errors using attention-based bidirectional long short-term memory and modulation spectrum","display_name":"Classification of causes of speech recognition errors using attention-based bidirectional long short-term memory and modulation spectrum","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3011644728","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023288","mag":"3011644728"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc47483.2019.9023288","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023288","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/A5002430203","display_name":"Jennifer Santoso","orcid":"https://orcid.org/0000-0001-7723-3396"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Jennifer Santoso","raw_affiliation_strings":["University of Tsukuba, Japan"],"affiliations":[{"raw_affiliation_string":"University of Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073170587","display_name":"Takeshi Yamada","orcid":"https://orcid.org/0000-0002-5744-8469"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takeshi Yamada","raw_affiliation_strings":["University of Tsukuba, Japan"],"affiliations":[{"raw_affiliation_string":"University of Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075702573","display_name":"Shoji Makino","orcid":"https://orcid.org/0000-0003-1934-640X"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoji Makino","raw_affiliation_strings":["University of Tsukuba, Japan"],"affiliations":[{"raw_affiliation_string":"University of Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5002430203"],"corresponding_institution_ids":["https://openalex.org/I146399215"],"apc_list":null,"apc_paid":null,"fwci":0.42,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.72868713,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"2","issue":null,"first_page":"302","last_page":"306"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"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":0.9991000294685364,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9919999837875366,"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/utterance","display_name":"Utterance","score":0.9444930553436279},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.793637752532959},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7914721965789795},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.7028377056121826},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44859352707862854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41810375452041626}],"concepts":[{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.9444930553436279},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.793637752532959},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7914721965789795},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.7028377056121826},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44859352707862854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41810375452041626}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc47483.2019.9023288","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023288","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1566256432","https://openalex.org/W2028825255","https://openalex.org/W2052922189","https://openalex.org/W2064675550","https://openalex.org/W2103253424","https://openalex.org/W2130689396","https://openalex.org/W2131694695","https://openalex.org/W2133564696","https://openalex.org/W2151534206","https://openalex.org/W2252236451","https://openalex.org/W2395582662","https://openalex.org/W2401725366","https://openalex.org/W2483962956","https://openalex.org/W2517194566","https://openalex.org/W2604490051","https://openalex.org/W2625297138","https://openalex.org/W2800146313","https://openalex.org/W2802402824","https://openalex.org/W2806051338","https://openalex.org/W6633947590","https://openalex.org/W6675639387","https://openalex.org/W6679434410","https://openalex.org/W6691212608","https://openalex.org/W6711912575","https://openalex.org/W6713149303"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W2333799855","https://openalex.org/W2351687372","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"In":[0,78],"this":[1,79],"paper,":[2,80],"we":[3,81,117,138],"address":[4],"the":[5,15,35,43,53,57,63,97,114,119,132,135,160,164,170,179],"problem":[6],"of":[7,45,62,76,108,121,134,181,187],"classifying":[8,185],"four":[9,148],"common":[10],"utterance":[11,16,54,68,122,150,191],"characteristics":[12,55,69,123],"related":[13],"to":[14,85,99,104,124],"speed,":[17],"which":[18],"cause":[19,186],"speech":[20],"recognition":[21,64],"errors.":[22],"We":[23],"previously":[24,171],"proposed":[25,136,161,172],"bidirectional":[26],"long":[27],"short-term":[28],"memory":[29],"(BLSTM)":[30],"as":[31,38],"a":[32,73,140,158],"classifier":[33,87,98],"and":[34,155],"modulation":[36,126],"spectrum":[37,127],"an":[39,83],"acoustic":[40],"feature.":[41],"However,":[42],"performance":[44,133],"it":[46],"is":[47],"still":[48],"insufficient,":[49],"since":[50],"BLSTM":[51,95,183],"classified":[52],"from":[56,67,113],"overall":[58,111],"utterance,":[59],"while":[60],"most":[61],"errors":[65,188],"resulted":[66],"occur":[70],"in":[71,184],"only":[72],"small":[74],"part":[75],"utterance.":[77],"propose":[82],"approach":[84],"enhance":[86],"by":[88,166],"using":[89,174],"attention":[90],"mechanism":[91],"(attention-based":[92],"BLSTM).":[93],"Attention-based":[94],"enables":[96],"weight":[100],"each":[101],"frame":[102],"according":[103],"its":[105],"importance":[106],"instead":[107],"directly":[109],"measuring":[110],"information":[112],"speech.":[115],"Furthermore,":[116],"investigate":[118],"correspondence":[120],"different":[125,149],"block":[128],"lengths.":[129],"To":[130],"evaluate":[131],"method,":[137],"conducted":[139],"classification":[141],"experiment":[142],"on":[143,190],"Japanese":[144],"conversational":[145],"speeches":[146],"with":[147,169],"characteristics:":[151],"`fast',":[152],"`slow',":[153],"`filler',":[154],"`stutter'.":[156],"As":[157],"result,":[159],"method":[162,173],"improved":[163],"F-score":[165],"0.033-0.129":[167],"compared":[168],"BLSTM.":[175],"This":[176],"result":[177],"confirms":[178],"effectiveness":[180],"attention-based":[182],"based":[189],"characteristics.":[192]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}