{"id":"https://openalex.org/W3015470971","doi":"https://doi.org/10.1109/icassp40776.2020.9054235","title":"Improving Proper Noun Recognition in End-To-End Asr by Customization of the Mwer Loss Criterion","display_name":"Improving Proper Noun Recognition in End-To-End Asr by Customization of the Mwer Loss Criterion","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015470971","doi":"https://doi.org/10.1109/icassp40776.2020.9054235","mag":"3015470971"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054235","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054235","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5037066965","display_name":"Cal Peyser","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":"Cal Peyser","raw_affiliation_strings":["Google Inc"],"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070513394","display_name":"Tara N. Sainath","orcid":"https://orcid.org/0000-0002-4126-6556"},"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":"Tara N. Sainath","raw_affiliation_strings":["Google Inc"],"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051090720","display_name":"Golan Pundak","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":"Golan Pundak","raw_affiliation_strings":["Google Inc"],"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5037066965"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":1.193,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.83175257,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"7789","last_page":"7793"},"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":0.9987000226974487,"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":0.996999979019165,"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":0.7934895753860474},{"id":"https://openalex.org/keywords/proper-noun","display_name":"Proper noun","score":0.6987495422363281},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6424214839935303},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6032148599624634},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.5724300742149353},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5520751476287842},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.524832546710968},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5128346085548401},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5023777484893799},{"id":"https://openalex.org/keywords/noun","display_name":"Noun","score":0.4898785948753357},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.48774224519729614},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.48065173625946045},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.42505162954330444},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16326820850372314}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7934895753860474},{"id":"https://openalex.org/C41417386","wikidata":"https://www.wikidata.org/wiki/Q147276","display_name":"Proper noun","level":2,"score":0.6987495422363281},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6424214839935303},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6032148599624634},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.5724300742149353},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5520751476287842},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.524832546710968},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5128346085548401},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5023777484893799},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.4898785948753357},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.48774224519729614},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.48065173625946045},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.42505162954330444},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16326820850372314},{"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:10.1109/icassp40776.2020.9054235","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054235","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2682542","https://openalex.org/W47568227","https://openalex.org/W1828163288","https://openalex.org/W1855892484","https://openalex.org/W1940872118","https://openalex.org/W2152731658","https://openalex.org/W2296237247","https://openalex.org/W2398767171","https://openalex.org/W2402242075","https://openalex.org/W2507771204","https://openalex.org/W2515439472","https://openalex.org/W2617258110","https://openalex.org/W2886319145","https://openalex.org/W2889163603","https://openalex.org/W2889494795","https://openalex.org/W2898599211","https://openalex.org/W2938947737","https://openalex.org/W2940322076","https://openalex.org/W2962760690","https://openalex.org/W2962765220","https://openalex.org/W2963240019","https://openalex.org/W2963362078","https://openalex.org/W2963739817","https://openalex.org/W2963747784","https://openalex.org/W2964525587","https://openalex.org/W2972741966","https://openalex.org/W2972880214","https://openalex.org/W2973122799","https://openalex.org/W3008181812","https://openalex.org/W6600109841","https://openalex.org/W6601939441","https://openalex.org/W6638749077","https://openalex.org/W6639156005","https://openalex.org/W6640362995","https://openalex.org/W6712890512","https://openalex.org/W6746924902","https://openalex.org/W6752739165","https://openalex.org/W6753477148","https://openalex.org/W6756319913"],"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":{"Proper":[0],"nouns":[1],"present":[2],"a":[3,15,27,33,58,66],"challenge":[4],"for":[5],"end-to-end":[6],"(E2E)":[7],"automatic":[8],"speech":[9],"recognition":[10],"(ASR)":[11],"systems":[12,42],"in":[13,93],"that":[14,31,48,61,106],"particular":[16],"name":[17],"may":[18,25],"appear":[19],"only":[20],"rarely":[21],"during":[22,124,129],"training,":[23],"and":[24,57],"have":[26],"pronunciation":[28],"similar":[29],"to":[30,100,137],"of":[32],"more":[34],"common":[35],"word.":[36],"Unlike":[37,112],"conventional":[38],"ASR":[39],"models,":[40],"E2E":[41],"lack":[43],"an":[44],"explicit":[45],"pronounciation":[46],"model":[47,60],"can":[49,62],"be":[50,63],"specifically":[51,107],"trained":[52,64],"with":[53],"proper":[54,109],"noun":[55,110],"pronounciations":[56],"language":[59],"on":[65,90,115,140],"large":[67],"text-only":[68],"corpus.":[69],"Past":[70],"work":[71,114],"has":[72],"addressed":[73],"this":[74,85,116,118],"issue":[75],"by":[76],"incorporating":[77],"additional":[78,82],"training":[79,99,125],"data":[80,123],"or":[81,126],"models.":[83],"In":[84],"paper,":[86],"we":[87],"instead":[88],"build":[89],"recent":[91],"advances":[92],"minimum":[94],"word":[95],"error":[96],"rate":[97],"(MWER)":[98],"develop":[101],"two":[102],"new":[103,122],"loss":[104],"criteria":[105],"emphasize":[108],"recognition.":[111],"past":[113],"problem,":[117],"method":[119],"requires":[120],"no":[121],"external":[127],"models":[128],"inference.":[130],"We":[131],"see":[132],"improvements":[133],"ranging":[134],"from":[135],"2%":[136],"7%":[138],"relative":[139],"several":[141],"relevant":[142],"benchmarks.":[143]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}