{"id":"https://openalex.org/W2957089051","doi":"https://doi.org/10.21437/interspeech.2019-2599","title":"Analyzing Phonetic and Graphemic Representations in End-to-End Automatic Speech Recognition","display_name":"Analyzing Phonetic and Graphemic Representations in End-to-End Automatic Speech Recognition","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2957089051","doi":"https://doi.org/10.21437/interspeech.2019-2599","mag":"2957089051"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-2599","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2599","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","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/1907.04224","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051184573","display_name":"Yonatan Belinkov","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yonatan Belinkov","raw_affiliation_strings":["Massachusetts Institute Of Technology#TAB#"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute Of Technology#TAB#","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693435","display_name":"Ahmed Ali","orcid":"https://orcid.org/0000-0002-9186-7544"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ahmed Ali","raw_affiliation_strings":["Massachusetts Institute Of Technology#TAB#"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute Of Technology#TAB#","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112758056","display_name":"James Glass","orcid":"https://orcid.org/0000-0002-3097-360X"},"institutions":[{"id":"https://openalex.org/I92528248","display_name":"Qatar Foundation","ror":"https://ror.org/01cawbq05","country_code":"QA","type":"funder","lineage":["https://openalex.org/I92528248"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"James Glass","raw_affiliation_strings":["QATAR FOUNDATION"],"affiliations":[{"raw_affiliation_string":"QATAR FOUNDATION","institution_ids":["https://openalex.org/I92528248"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5051184573"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":0.5786,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.75461805,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"81","last_page":"85"},"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/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9983999729156494,"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":0.8214050531387329},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.8152007460594177},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6479230523109436},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.6417997479438782},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5967037677764893},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.551151692867279},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5092674493789673},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49382051825523376},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13660454750061035}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8214050531387329},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.8152007460594177},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6479230523109436},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.6417997479438782},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5967037677764893},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.551151692867279},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5092674493789673},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49382051825523376},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13660454750061035},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2019-2599","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2599","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1907.04224","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.04224","pdf_url":"https://arxiv.org/pdf/1907.04224","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2957089051","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1907.04224","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.1907.04224","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1907.04224","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:1907.04224","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.04224","pdf_url":"https://arxiv.org/pdf/1907.04224","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2957089051.pdf","grobid_xml":"https://content.openalex.org/works/W2957089051.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1990501283","https://openalex.org/W2127141656","https://openalex.org/W2193413348","https://openalex.org/W2250357346","https://openalex.org/W2295676751","https://openalex.org/W2327501763","https://openalex.org/W2402146185","https://openalex.org/W2511774920","https://openalex.org/W2586148577","https://openalex.org/W2586568968","https://openalex.org/W2748318213","https://openalex.org/W2756127416","https://openalex.org/W2758849341","https://openalex.org/W2888760383","https://openalex.org/W2888995442","https://openalex.org/W2890704021","https://openalex.org/W2899073901","https://openalex.org/W2906152891","https://openalex.org/W2950657340","https://openalex.org/W2953190524","https://openalex.org/W2962753610","https://openalex.org/W2962799131","https://openalex.org/W2962813140","https://openalex.org/W2963077089","https://openalex.org/W2963211739","https://openalex.org/W2963430224","https://openalex.org/W2963540920","https://openalex.org/W2964060510","https://openalex.org/W3105148948"],"related_works":["https://openalex.org/W2972808286","https://openalex.org/W2913960647","https://openalex.org/W2964309797","https://openalex.org/W2894778092","https://openalex.org/W3016262400","https://openalex.org/W3034931686","https://openalex.org/W2891539192","https://openalex.org/W2086667971","https://openalex.org/W2293858598","https://openalex.org/W2888760383","https://openalex.org/W2786102402","https://openalex.org/W2153986034","https://openalex.org/W1963929757","https://openalex.org/W3007776460","https://openalex.org/W3104842308","https://openalex.org/W1546843341","https://openalex.org/W3201305507","https://openalex.org/W3153839229","https://openalex.org/W2950658695","https://openalex.org/W2170353620"],"abstract_inverted_index":{"End-to-end":[0],"neural":[1,58,146],"network":[2,59,78],"systems":[3],"for":[4,27],"automatic":[5],"speech":[6],"recognition":[7],"(ASR)":[8],"are":[9,61,138],"trained":[10],"from":[11],"acoustic":[12,28],"features":[13],"to":[14,19,69],"text":[15],"transcriptions.":[16],"In":[17,86],"contrast":[18],"modular":[20],"ASR":[21,98],"systems,":[22],"which":[23],"contain":[24],"separately-trained":[25],"components":[26],"modeling,":[29,34],"pronunciation":[30],"lexicon,":[31],"and":[32,42,79,113,126,128],"language":[33],"the":[35,44,49,53,71,77,91,102,144],"end-to-end":[36,97],"paradigm":[37],"is":[38,65],"both":[39],"conceptually":[40],"simpler":[41],"has":[43],"potential":[45],"benefit":[46],"of":[47,73,76,107,143],"training":[48],"entire":[50],"system":[51],"on":[52],"end":[54],"task.":[55],"However,":[56],"such":[57],"models":[60],"more":[62],"opaque:":[63],"it":[64,82],"not":[66],"clear":[67],"how":[68,135],"interpret":[70],"role":[72],"different":[74,118,136,141],"parts":[75],"what":[80],"information":[81],"learns":[83],"during":[84],"training.":[85],"this":[87],"paper,":[88],"we":[89],"analyze":[90],"learned":[92],"internal":[93],"representations":[94],"in":[95,105,134,140],"an":[96],"model.":[99],"We":[100,121],"evaluate":[101],"representation":[103],"quality":[104],"terms":[106],"several":[108],"classification":[109],"tasks,":[110],"comparing":[111],"phonemes":[112],"graphemes,":[114],"as":[115,117],"well":[116],"articulatory":[119],"features.":[120],"study":[122],"two":[123],"languages":[124],"(English":[125],"Arabic)":[127],"three":[129],"datasets,":[130],"finding":[131],"remarkable":[132],"consistency":[133],"properties":[137],"represented":[139],"layers":[142],"deep":[145],"network.":[147]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}