{"id":"https://openalex.org/W2894164357","doi":"https://doi.org/10.1109/slt.2018.8639043","title":"From Audio to Semantics: Approaches to End-to-End Spoken Language Understanding","display_name":"From Audio to Semantics: Approaches to End-to-End Spoken Language Understanding","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2894164357","doi":"https://doi.org/10.1109/slt.2018.8639043","mag":"2894164357"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2018.8639043","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639043","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","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/A5037705635","display_name":"Parisa Haghani","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Parisa Haghani","raw_affiliation_strings":["Google Inc., USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000078382","display_name":"Arun Narayanan","orcid":"https://orcid.org/0009-0008-3325-8928"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arun Narayanan","raw_affiliation_strings":["Google Inc., USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049614700","display_name":"Michiel Bacchiani","orcid":"https://orcid.org/0000-0003-4527-0197"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michiel Bacchiani","raw_affiliation_strings":["Google Inc., USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008420109","display_name":"Galen Chuang","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Galen Chuang","raw_affiliation_strings":["Google Inc., USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016601028","display_name":"Neeraj Gaur","orcid":"https://orcid.org/0000-0002-5926-9966"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Neeraj Gaur","raw_affiliation_strings":["Google Inc., USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103874391","display_name":"Pedro J. Moreno","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pedro Moreno","raw_affiliation_strings":["Google Inc., USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032640894","display_name":"Rohit Prabhavalkar","orcid":"https://orcid.org/0000-0001-5331-6058"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rohit Prabhavalkar","raw_affiliation_strings":["Google Inc., USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008909213","display_name":"Zhongdi Qu","orcid":"https://orcid.org/0009-0002-7789-712X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhongdi Qu","raw_affiliation_strings":["Google Inc., USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064711844","display_name":"Austin Waters","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Austin Waters","raw_affiliation_strings":["Google Inc., USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5037705635"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":15.6369,"has_fulltext":false,"cited_by_count":138,"citation_normalized_percentile":{"value":0.99144928,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"720","last_page":"726"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9994999766349792,"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/T10181","display_name":"Natural Language Processing Techniques","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8507466316223145},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6352664232254028},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5947777032852173},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5552727580070496},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5549578666687012},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5477480292320251},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.5445412397384644},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5364317297935486},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5304298400878906},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5285526514053345},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5239500999450684},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5054621696472168},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.5030476450920105},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4787708818912506},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.463382363319397},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.44788262248039246},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4355087876319885},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4235954284667969},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1765512228012085},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09463170170783997}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8507466316223145},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6352664232254028},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5947777032852173},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5552727580070496},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5549578666687012},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5477480292320251},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.5445412397384644},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5364317297935486},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5304298400878906},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5285526514053345},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5239500999450684},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5054621696472168},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.5030476450920105},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4787708818912506},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.463382363319397},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.44788262248039246},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4355087876319885},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4235954284667969},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1765512228012085},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09463170170783997},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/slt.2018.8639043","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639043","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W648786980","https://openalex.org/W648947103","https://openalex.org/W1522301498","https://openalex.org/W1649407914","https://openalex.org/W2007261869","https://openalex.org/W2035438624","https://openalex.org/W2064675550","https://openalex.org/W2127141656","https://openalex.org/W2130942839","https://openalex.org/W2131774270","https://openalex.org/W2133564696","https://openalex.org/W2144578941","https://openalex.org/W2157331557","https://openalex.org/W2327501763","https://openalex.org/W2402144811","https://openalex.org/W2473329891","https://openalex.org/W2511962886","https://openalex.org/W2525778437","https://openalex.org/W2606722458","https://openalex.org/W2622203030","https://openalex.org/W2622301280","https://openalex.org/W2800921391","https://openalex.org/W2891229414","https://openalex.org/W2913340405","https://openalex.org/W2953384591","https://openalex.org/W2962715022","https://openalex.org/W2962765220","https://openalex.org/W2962824709","https://openalex.org/W2963266252","https://openalex.org/W2963288440","https://openalex.org/W2963403868","https://openalex.org/W2963747784","https://openalex.org/W2963842982","https://openalex.org/W2963920996","https://openalex.org/W2963974889","https://openalex.org/W2963980299","https://openalex.org/W2964121744","https://openalex.org/W2964308564","https://openalex.org/W4385245566","https://openalex.org/W6621543089","https://openalex.org/W6629052376","https://openalex.org/W6631190155","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6713134421","https://openalex.org/W6725841421","https://openalex.org/W6739901393","https://openalex.org/W6746892368","https://openalex.org/W6746924902"],"related_works":["https://openalex.org/W2916997151","https://openalex.org/W2949174760","https://openalex.org/W1566315437","https://openalex.org/W2594897229","https://openalex.org/W4221142855","https://openalex.org/W2151348424","https://openalex.org/W2050138804","https://openalex.org/W767271433","https://openalex.org/W4290708361","https://openalex.org/W2129812225"],"abstract_inverted_index":{"Conventional":[0],"spoken":[1],"language":[2,24],"understanding":[3,25,58],"systems":[4],"consist":[5],"of":[6,39,99,117],"two":[7],"main":[8],"components:":[9],"an":[10,78,90],"automatic":[11],"speech":[12],"recognition":[13],"module":[14,26],"that":[15,27,72,87],"converts":[16],"audio":[17,55],"to":[18,56,120],"a":[19,22,37,60,83],"transcript,":[20],"and":[21,42,66,107,132],"natural":[23],"transforms":[28],"the":[29,97,100,104,111],"resulting":[30],"text":[31,92],"(or":[32],"top":[33],"N":[34],"hypotheses)":[35],"into":[36],"set":[38],"domains,":[40],"intents,":[41],"arguments.":[43],"These":[44],"modules":[45,75],"are":[46],"typically":[47],"optimized":[48],"independently.":[49],"In":[50],"this":[51],"paper,":[52],"we":[53],"formulate":[54],"semantic":[57],"as":[59],"sequence-to-sequence":[61],"problem":[62],"[1].":[63],"We":[64],"propose":[65],"compare":[67],"various":[68],"encoder-decoder":[69],"based":[70],"approaches":[71],"optimize":[73],"both":[74],"jointly,":[76],"in":[77],"end-to-end":[79],"manner.":[80],"Evaluations":[81],"on":[82],"real-world":[84],"task":[85],"show":[86],"1)":[88],"having":[89],"intermediate":[91],"representation":[93],"is":[94],"crucial":[95],"for":[96],"quality":[98],"predicted":[101],"semantics,":[102],"especially":[103],"intent":[105,133],"arguments":[106],"2)":[108],"jointly":[109,126],"optimizing":[110],"full":[112],"system":[113],"improves":[114,138],"overall":[115],"accuracy":[116],"prediction.":[118],"Compared":[119],"independently":[121],"trained":[122,127],"models,":[123],"our":[124],"best":[125],"model":[128],"achieves":[129],"similar":[130],"domain":[131],"prediction":[134],"F1":[135],"scores,":[136],"but":[137],"argument":[139],"word":[140],"error":[141],"rate":[142],"by":[143],"18%":[144],"relative.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":52},{"year":2020,"cited_by_count":35},{"year":2019,"cited_by_count":8}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}