{"id":"https://openalex.org/W3034931686","doi":"https://doi.org/10.1145/3397271.3401050","title":"Using Phoneme Representations to Build Predictive Models Robust to ASR Errors","display_name":"Using Phoneme Representations to Build Predictive Models Robust to ASR Errors","publication_year":2020,"publication_date":"2020-07-25","ids":{"openalex":"https://openalex.org/W3034931686","doi":"https://doi.org/10.1145/3397271.3401050","mag":"3034931686"},"language":"en","primary_location":{"id":"doi:10.1145/3397271.3401050","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3397271.3401050","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3397271.3401050","source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3397271.3401050","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049221759","display_name":"Anjie Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anjie Fang","raw_affiliation_strings":["Amazon, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon, Seattle, WA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093826503","display_name":"Simone Filice","orcid":"https://orcid.org/0009-0002-6735-9950"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Simone Filice","raw_affiliation_strings":["Amazon, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon, Seattle, WA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000400985","display_name":"Nut Limsopatham","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nut Limsopatham","raw_affiliation_strings":["Microsoft AI, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft AI, Seattle, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024656386","display_name":"Oleg Rokhlenko","orcid":"https://orcid.org/0000-0002-7158-9161"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oleg Rokhlenko","raw_affiliation_strings":["Amazon, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon, Seattle, WA, USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.495,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.85901517,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"699","last_page":"708"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.854911208152771},{"id":"https://openalex.org/keywords/treebank","display_name":"Treebank","score":0.7855385541915894},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6241843700408936},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5862600803375244},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.559392511844635},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5246437191963196},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5228859782218933},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.4895354211330414},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.29778793454170227},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.13750767707824707},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09772801399230957}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.854911208152771},{"id":"https://openalex.org/C206134035","wikidata":"https://www.wikidata.org/wiki/Q811525","display_name":"Treebank","level":3,"score":0.7855385541915894},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6241843700408936},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5862600803375244},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.559392511844635},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5246437191963196},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5228859782218933},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.4895354211330414},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.29778793454170227},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.13750767707824707},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09772801399230957},{"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:10.1145/3397271.3401050","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3397271.3401050","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3397271.3401050","source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3397271.3401050","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3397271.3401050","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3397271.3401050","source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3034931686.pdf","grobid_xml":"https://content.openalex.org/works/W3034931686.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W191484614","https://openalex.org/W1494198834","https://openalex.org/W1496801689","https://openalex.org/W1516184288","https://openalex.org/W1832693441","https://openalex.org/W2041670430","https://openalex.org/W2064675550","https://openalex.org/W2070246124","https://openalex.org/W2074231493","https://openalex.org/W2102113734","https://openalex.org/W2114524997","https://openalex.org/W2145077480","https://openalex.org/W2250539671","https://openalex.org/W2251939518","https://openalex.org/W2296237247","https://openalex.org/W2507739667","https://openalex.org/W2509809153","https://openalex.org/W2538246917","https://openalex.org/W2594395650","https://openalex.org/W2608050011","https://openalex.org/W2781461271","https://openalex.org/W2800921391","https://openalex.org/W2891229414","https://openalex.org/W2896457183","https://openalex.org/W2900116145","https://openalex.org/W2945524287","https://openalex.org/W2949888546","https://openalex.org/W2950133940","https://openalex.org/W2950577311","https://openalex.org/W2951559648","https://openalex.org/W2962739339","https://openalex.org/W2963323070","https://openalex.org/W2972584841","https://openalex.org/W4205807230","https://openalex.org/W4285719527","https://openalex.org/W6631036137"],"related_works":["https://openalex.org/W3142119062","https://openalex.org/W131522978","https://openalex.org/W159209093","https://openalex.org/W589103562","https://openalex.org/W1991220724","https://openalex.org/W2251234095","https://openalex.org/W2250768577","https://openalex.org/W2160717663","https://openalex.org/W2250721770","https://openalex.org/W4293479148"],"abstract_inverted_index":{"Even":[0],"though":[1],"Automatic":[2],"Speech":[3],"Recognition":[4],"(ASR)":[5],"systems":[6],"significantly":[7,82,188],"improved":[8],"over":[9],"the":[10,28,57,84,124,178,206],"last":[11],"decade,":[12],"they":[13,21],"still":[14],"introduce":[15],"a":[16,42],"lot":[17],"of":[18,27,69,76,86,154],"errors":[19,34,81],"when":[20],"transcribe":[22],"voice":[23],"to":[24,56,109,128,205],"text.":[25],"One":[26],"most":[29],"common":[30,173],"reasons":[31],"for":[32],"these":[33,195],"is":[35],"phonetic":[36],"confusion":[37],"between":[38],"similar-sounding":[39],"expressions.":[40],"As":[41],"result,":[43],"ASR":[44,121,152],"transcriptions":[45,122,153,186],"often":[46],"contain":[47],"\"quasi-oronyms\",":[48],"i.e.,":[49],"words":[50],"or":[51,71],"phrases":[52],"that":[53,61,172],"sound":[54],"similar":[55],"source":[58],"ones,":[59],"but":[60],"have":[62],"completely":[63],"different":[64],"semantics":[65],"(e.g.,":[66,93,139],"\"win\"":[67],"instead":[68,75],"\"when\"":[70],"\"accessible":[72,77],"on":[73,201],"defecting\"":[74],"and":[78,99,144,166,170,187],"affecting\").":[79],"These":[80],"affect":[83],"performance":[85],"downstream":[87],"Natural":[88],"Language":[89],"Understanding":[90],"(NLU)":[91],"models":[92,106,200],"intent":[94],"classification,":[95],"slot":[96],"filling,":[97],"etc.)":[98],"impair":[100],"user":[101],"experience.":[102],"To":[103,142],"make":[104],"NLU":[105],"more":[107],"robust":[108],"such":[110],"errors,":[111],"we":[112,119,149,193],"propose":[113],"novel":[114],"phonetic-aware":[115],"text":[116],"representations.":[117],"Specifically,":[118],"represent":[120],"at":[123],"phoneme":[125,147,180],"level,":[126],"aiming":[127],"capture":[129],"pronunciation":[130],"similarities,":[131],"which":[132],"are":[133],"typically":[134],"neglected":[135],"in":[136],"word-level":[137],"representations":[138,181],"word":[140],"embeddings).":[141],"train":[143],"evaluate":[145],"our":[146,199],"representations,":[148],"generate":[150],"noisy":[151,185],"four":[155],"existing":[156],"datasets":[157],"-":[158,169],"Stanford":[159],"Sentiment":[160],"Treebank,":[161],"SQuAD,":[162],"TREC":[163],"Question":[164],"Classification":[165],"Subjectivity":[167],"Analysis":[168],"show":[171],"neural":[174],"network":[175],"architectures":[176],"exploiting":[177],"proposed":[179],"can":[182],"effectively":[183],"handle":[184],"outperform":[189],"state-of-the-art":[190],"baselines.":[191],"Finally,":[192],"confirm":[194],"results":[196],"by":[197],"testing":[198],"real":[202],"utterances":[203],"spoken":[204],"Alexa":[207],"virtual":[208],"assistant.":[209]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}