{"id":"https://openalex.org/W3081494755","doi":"https://doi.org/10.21437/interspeech.2020-1465","title":"Improving Tail Performance of a Deliberation E2E ASR Model Using a Large Text Corpus","display_name":"Improving Tail Performance of a Deliberation E2E ASR Model Using a Large Text Corpus","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3081494755","doi":"https://doi.org/10.21437/interspeech.2020-1465","mag":"3081494755"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1465","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1465","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/2008.10491","any_repository_has_fulltext":true},"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,,,,,"],"affiliations":[{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060420622","display_name":"Sepand Mavandadi","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":"Sepand Mavandadi","raw_affiliation_strings":["Google,,,,,"],"affiliations":[{"raw_affiliation_string":"Google,,,,,","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,,,,,"],"affiliations":[{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004185134","display_name":"James Apfel","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":"James Apfel","raw_affiliation_strings":["Google,,,,,"],"affiliations":[{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112901893","display_name":"Ruoming Pang","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":"Ruoming Pang","raw_affiliation_strings":["Google,,,,,"],"affiliations":[{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101051347","display_name":"Shankar Kumar","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":"Shankar Kumar","raw_affiliation_strings":["Google,,,,,"],"affiliations":[{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5037066965"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.9601,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.81165814,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9997000098228455,"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":0.9988999962806702,"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":0.8079913258552551},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.7543315291404724},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6941573023796082},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5905211567878723},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5687143206596375},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5554246306419373},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5514526963233948},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5414214134216309},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5405328273773193},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.523618757724762},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48451536893844604},{"id":"https://openalex.org/keywords/beam-search","display_name":"Beam search","score":0.45436978340148926},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.41598576307296753},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41383683681488037},{"id":"https://openalex.org/keywords/search-algorithm","display_name":"Search algorithm","score":0.20327875018119812},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11919361352920532}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8079913258552551},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.7543315291404724},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6941573023796082},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5905211567878723},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5687143206596375},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5554246306419373},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5514526963233948},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5414214134216309},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5405328273773193},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.523618757724762},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48451536893844604},{"id":"https://openalex.org/C19889080","wikidata":"https://www.wikidata.org/wiki/Q2835852","display_name":"Beam search","level":3,"score":0.45436978340148926},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.41598576307296753},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41383683681488037},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.20327875018119812},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11919361352920532},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2020-1465","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1465","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2008.10491","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.10491","pdf_url":"https://arxiv.org/pdf/2008.10491","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":null,"raw_type":"text"},{"id":"mag:3081494755","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2008.10491.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.2008.10491","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2008.10491","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:2008.10491","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.10491","pdf_url":"https://arxiv.org/pdf/2008.10491","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":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.49000000953674316,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3081494755.pdf","grobid_xml":"https://content.openalex.org/works/W3081494755.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W2682542","https://openalex.org/W1524333225","https://openalex.org/W1828163288","https://openalex.org/W1915251500","https://openalex.org/W1966147466","https://openalex.org/W2116361377","https://openalex.org/W2152731658","https://openalex.org/W2259472270","https://openalex.org/W2577366047","https://openalex.org/W2611669587","https://openalex.org/W2739427748","https://openalex.org/W2747467128","https://openalex.org/W2888779557","https://openalex.org/W2962760690","https://openalex.org/W2962765220","https://openalex.org/W2963122170","https://openalex.org/W2963240019","https://openalex.org/W2963362078","https://openalex.org/W2963747784","https://openalex.org/W2963827914","https://openalex.org/W2964539095","https://openalex.org/W2973122799","https://openalex.org/W2990501692","https://openalex.org/W3008037978","https://openalex.org/W3011339933","https://openalex.org/W3015470971"],"related_works":["https://openalex.org/W3096815019","https://openalex.org/W3137489363","https://openalex.org/W3136786651","https://openalex.org/W2913041008","https://openalex.org/W2992448548","https://openalex.org/W2900312178","https://openalex.org/W3205893931","https://openalex.org/W3208017279","https://openalex.org/W3105804405","https://openalex.org/W3163339532","https://openalex.org/W114932164","https://openalex.org/W2766572290","https://openalex.org/W2949788262","https://openalex.org/W2890197052","https://openalex.org/W3097573669","https://openalex.org/W2914151612","https://openalex.org/W2520176975","https://openalex.org/W3126699312","https://openalex.org/W2736984005","https://openalex.org/W3143377973"],"abstract_inverted_index":{"End-to-end":[0],"(E2E)":[1],"automatic":[2],"speech":[3,17],"recognition":[4,40],"(ASR)":[5],"systems":[6],"lack":[7],"the":[8,22,27,39,97,121,132,141,149,170],"distinct":[9],"language":[10],"model":[11,23,69,124],"(LM)":[12],"component":[13],"that":[14,44,128,147,173],"characterizes":[15],"traditional":[16],"systems.":[18],"While":[19,52],"this":[20,101],"simplifies":[21],"architecture,":[24],"it":[25,73,85],"complicates":[26],"task":[28],"of":[29,41,123,131,172],"incorporating":[30,62,148],"text-only":[31],"data":[32],"into":[33,66,114],"training,":[34],"which":[35],"is":[36],"important":[37],"to":[38,89,93,107],"tail":[42],"words":[43],"do":[45],"not":[46,75],"occur":[47],"often":[48],"in":[49,96,151],"audio-text":[50],"pairs.":[51],"shallow":[53,105,160],"fusion":[54,106,161],"has":[55,74,86],"been":[56,77,87],"proposed":[57],"as":[58],"a":[59,63,109,115],"method":[60],"for":[61,79],"pre-trained":[64],"LM":[65,150],"an":[67],"E2E":[68],"at":[70],"inference":[71],"time,":[72],"yet":[76],"explored":[78],"very":[80,91,110],"large":[81,111],"text":[82,112],"corpora,":[83],"and":[84,126],"shown":[88],"be":[90,136],"sensitive":[92],"hyperparameter":[94,167],"settings":[95],"beam":[98],"search.":[99],"In":[100],"work,":[102],"we":[103,145],"apply":[104],"incorporate":[108],"corpus":[113],"state-of-the-art":[116],"E2EASR":[117],"model.":[118],"We":[119],"explore":[120],"impact":[122],"size":[125],"show":[127,146],"intelligent":[129],"pruning":[130],"training":[133],"set":[134],"can":[135],"more":[137],"effective":[138],"than":[139],"increasing":[140],"parameter":[142],"count.":[143],"Additionally,":[144],"minimum":[152],"word":[153],"error":[154],"rate":[155],"(MWER)":[156],"fine":[157],"tuning":[158,174],"makes":[159],"far":[162],"less":[163],"dependent":[164],"on":[165],"optimal":[166],"settings,":[168],"reducing":[169],"difficulty":[171],"problem.":[175]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}