{"id":"https://openalex.org/W2604904674","doi":"https://doi.org/10.21437/interspeech.2017-1117","title":"Learning Similarity Functions for Pronunciation Variations","display_name":"Learning Similarity Functions for Pronunciation Variations","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2604904674","doi":"https://doi.org/10.21437/interspeech.2017-1117","mag":"2604904674"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-1117","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1117","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1703.09817","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039907756","display_name":"Einat Naaman","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Einat Naaman","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005191803","display_name":"Yossi Adi","orcid":"https://orcid.org/0000-0003-2237-3898"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yossi Adi","raw_affiliation_strings":["Bar-Ilan University, Ramat Gan, Israel"],"affiliations":[{"raw_affiliation_string":"Bar-Ilan University, Ramat Gan, Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008847407","display_name":"Joseph Keshet","orcid":"https://orcid.org/0000-0003-2332-5783"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Joseph Keshet","raw_affiliation_strings":["Bar-Ilan University, Ramat Gan, Israel"],"affiliations":[{"raw_affiliation_string":"Bar-Ilan University, Ramat Gan, Israel","institution_ids":["https://openalex.org/I13955877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5039907756"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.45835928,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.68734672,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2561","last_page":"2565"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10201","display_name":"Speech Recognition and Synthesis","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":0.9984999895095825,"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":0.9970999956130981,"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/pronunciation","display_name":"Pronunciation","score":0.8281705379486084},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.8065266609191895},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8020939230918884},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7046819925308228},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7009681463241577},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6481627821922302},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5787748694419861},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5468520522117615},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4844074845314026},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.4666896462440491},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14728453755378723}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.8281705379486084},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.8065266609191895},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8020939230918884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7046819925308228},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7009681463241577},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6481627821922302},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5787748694419861},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5468520522117615},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4844074845314026},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.4666896462440491},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14728453755378723},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2017-1117","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1117","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1703.09817","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1703.09817","pdf_url":"https://arxiv.org/pdf/1703.09817","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2604904674","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1703.09817.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1703.09817","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1703.09817","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1703.09817","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1703.09817","pdf_url":"https://arxiv.org/pdf/1703.09817","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2604904674.pdf","grobid_xml":"https://content.openalex.org/works/W2604904674.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W114725541","https://openalex.org/W196692374","https://openalex.org/W1608231129","https://openalex.org/W1916501714","https://openalex.org/W2068447135","https://openalex.org/W2110485445","https://openalex.org/W2118521812","https://openalex.org/W2137368806","https://openalex.org/W2146502635","https://openalex.org/W2150750246","https://openalex.org/W2151244813","https://openalex.org/W2154092232","https://openalex.org/W2187089797","https://openalex.org/W2190506272","https://openalex.org/W2251532530"],"related_works":["https://openalex.org/W2963306023","https://openalex.org/W199152779","https://openalex.org/W1521601951","https://openalex.org/W2625701092","https://openalex.org/W2404544250","https://openalex.org/W2214043111","https://openalex.org/W2121694817","https://openalex.org/W1579089397","https://openalex.org/W1994437175","https://openalex.org/W2937402758","https://openalex.org/W1984324186","https://openalex.org/W1550092932","https://openalex.org/W1583757088","https://openalex.org/W3119673337","https://openalex.org/W2107959623","https://openalex.org/W1483055307","https://openalex.org/W2131154411","https://openalex.org/W1565662837","https://openalex.org/W2026197747","https://openalex.org/W2165280259"],"abstract_inverted_index":{"A":[0],"significant":[1],"source":[2],"of":[3,62,73,86,110,151,158,164,170],"errors":[4],"in":[5,18,115],"Automatic":[6],"Speech":[7],"Recognition":[8],"(ASR)":[9],"systems":[10,25],"is":[11,137,145],"due":[12],"to":[13,105,130,186],"pronunciation":[14,112],"variations":[15],"which":[16,123,189],"occur":[17],"spontaneous":[19],"and":[20,58,92,96,142],"conversational":[21,173],"speech.":[22],"Usually":[23],"ASR":[24,117],"use":[26],"a":[27,46,168],"finite":[28],"lexicon":[29],"that":[30,178],"provides":[31],"one":[32],"or":[33,66,114],"more":[34],"pronunciations":[35,53,61,72],"for":[36],"each":[37],"word.":[38],"In":[39],"this":[40,180],"paper,":[41],"we":[42],"focus":[43],"on":[44,126,139,147,161,179,192],"learning":[45,87,148],"similarity":[47,133],"function":[48],"between":[49,90],"two":[50,70,121],"pronunciations.":[51,153],"The":[52,135],"can":[54,68,101],"be":[55,69,103],"the":[56,59,63,88,108,111,132,143,149,152,156,162,171],"canonical":[57],"surface":[60,71],"same":[64],"word":[65,98],"they":[67],"different":[74],"words.":[75],"This":[76],"task":[77,163,181],"generalizes":[78],"problems":[79],"such":[80],"as":[81],"lexical":[82,165],"access":[83,166],"(the":[84],"problem":[85],"mapping":[89],"words":[91],"their":[93],"possible":[94],"pronunciations),":[95],"defining":[97],"neighborhoods.":[99],"It":[100],"also":[102],"used":[104],"dynamically":[106],"increase":[107],"size":[109],"lexicon,":[113],"predicting":[116],"errors.":[118],"We":[119,154],"propose":[120],"methods,":[122],"are":[124,184,190],"based":[125,138,146,191],"recurrent":[127],"neural":[128],"networks,":[129],"learn":[131],"function.":[134],"first":[136],"binary":[140],"classification,":[141],"second":[144],"ranking":[150],"demonstrate":[155],"efficiency":[157],"our":[159,182],"approach":[160],"using":[167],"subset":[169],"Switchboard":[172],"speech":[174],"corpus.":[175],"Results":[176],"suggest":[177],"methods":[183,188],"superior":[185],"previous":[187],"graphical":[193],"Bayesian":[194],"methods.":[195]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}