{"id":"https://openalex.org/W2800921391","doi":"https://doi.org/10.1109/icassp.2018.8461598","title":"Incorporating ASR Errors with Attention-Based, Jointly Trained RNN for Intent Detection and Slot Filling","display_name":"Incorporating ASR Errors with Attention-Based, Jointly Trained RNN for Intent Detection and Slot Filling","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2800921391","doi":"https://doi.org/10.1109/icassp.2018.8461598","mag":"2800921391"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461598","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461598","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5066593161","display_name":"Raphael Schumann","orcid":null},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Raphael Schumann","raw_affiliation_strings":["Heidelberg University, Institute for Computational Linguistics, Heidelberg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Heidelberg University, Institute for Computational Linguistics, Heidelberg, Germany","institution_ids":["https://openalex.org/I223822909"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026807873","display_name":"Pongtep Angkititrakul","orcid":"https://orcid.org/0000-0001-9739-2052"},"institutions":[{"id":"https://openalex.org/I4210120115","display_name":"Robert Bosch (United States)","ror":"https://ror.org/02venad53","country_code":"US","type":"company","lineage":["https://openalex.org/I4210120115","https://openalex.org/I889804353"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pongtep Angkititrakul","raw_affiliation_strings":["Robert Bosch LLC, MHI-Conversational AI, Sunnyvale, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robert Bosch LLC, MHI-Conversational AI, Sunnyvale, CA","institution_ids":["https://openalex.org/I4210120115"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6059","last_page":"6063"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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":0.9994000196456909,"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/utterance","display_name":"Utterance","score":0.8592628240585327},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8207240104675293},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7829945087432861},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6729896068572998},{"id":"https://openalex.org/keywords/decodes","display_name":"Decodes","score":0.6312669515609741},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.566132128238678},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5488600730895996},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5177430510520935},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.48743656277656555},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.46591687202453613},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45213595032691956},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.4416516125202179},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.43321534991264343},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.36260855197906494},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.34626278281211853},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3406771123409271},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18416765332221985}],"concepts":[{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.8592628240585327},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8207240104675293},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7829945087432861},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6729896068572998},{"id":"https://openalex.org/C2778858076","wikidata":"https://www.wikidata.org/wiki/Q5249539","display_name":"Decodes","level":3,"score":0.6312669515609741},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.566132128238678},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5488600730895996},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5177430510520935},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.48743656277656555},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.46591687202453613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45213595032691956},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.4416516125202179},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.43321534991264343},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.36260855197906494},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.34626278281211853},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3406771123409271},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18416765332221985},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461598","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461598","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.46000000834465027,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W648786980","https://openalex.org/W854541894","https://openalex.org/W1522301498","https://openalex.org/W1550863320","https://openalex.org/W1902237438","https://openalex.org/W1971034924","https://openalex.org/W2064675550","https://openalex.org/W2077302143","https://openalex.org/W2094472029","https://openalex.org/W2098921539","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2137871902","https://openalex.org/W2147880316","https://openalex.org/W2157331557","https://openalex.org/W2262249176","https://openalex.org/W2280798142","https://openalex.org/W2766724669","https://openalex.org/W2951562155","https://openalex.org/W2963974889","https://openalex.org/W6621543089","https://openalex.org/W6623517193","https://openalex.org/W6631190155","https://openalex.org/W6636392717","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6682082992","https://openalex.org/W6692962889","https://openalex.org/W6695220544"],"related_works":["https://openalex.org/W1523025284","https://openalex.org/W1566315437","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2594897229","https://openalex.org/W2050138804","https://openalex.org/W767271433","https://openalex.org/W4290708361","https://openalex.org/W2129812225","https://openalex.org/W2523799048"],"abstract_inverted_index":{"The":[0,21,63,92],"real-world":[1],"performance":[2],"of":[3,36,51,59,100],"slot":[4,55,90,129],"filling":[5,56,130],"and":[6,24,34,54,77,131],"intent":[7,52,72,138],"detection":[8,53],"task":[9],"generally":[10],"degrades":[11],"due":[12],"to":[13],"transcription":[14],"errors":[15,26,80],"generated":[16],"by":[17],"speech":[18,28,60],"recognition":[19,61],"engine.":[20],"insertion,":[22],"deletion,":[23],"mis-recognition":[25],"from":[27,74],"recognizer's":[29],"front-end":[30],"cause":[31],"the":[32,37,71,82,89,98,113,121],"mis-interpretation":[33],"mis-alignment":[35],"language":[38],"understanding":[39,103],"models.":[40],"In":[41],"this":[42],"work,":[43],"we":[44],"propose":[45],"a":[46,101],"new":[47],"jointly":[48],"trained":[49],"model":[50,115,123],"with":[57],"consideration":[58],"errors.":[62],"attention-based":[64],"encoder-decoder":[65],"recurrent":[66],"neural":[67],"network":[68],"first":[69],"decodes":[70],"information":[73],"an":[75,105],"utterance,":[76],"then":[78],"corrects":[79],"in":[81],"word":[83],"sequence,":[84],"if":[85],"any,":[86],"before":[87],"extracting":[88],"information.":[91],"triple":[93],"joint":[94,122],"training":[95],"framework":[96],"maximizes":[97],"probability":[99],"correct":[102],"given":[104],"input":[106],"utterance.":[107],"Our":[108],"experimental":[109],"results":[110],"showed":[111],"that":[112],"proposed":[114],"obtained":[116],"2.87%":[117],"absolute":[118,133],"gain":[119],"over":[120],"without":[124],"ASR":[125],"error":[126,134],"correction":[127],"for":[128,137],"0.73%":[132],"rate":[135],"reduction":[136],"detection.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}