{"id":"https://openalex.org/W3095315336","doi":"https://doi.org/10.21437/interspeech.2020-2357","title":"Word Error Rate Estimation Without ASR Output: e-WER2","display_name":"Word Error Rate Estimation Without ASR Output: e-WER2","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3095315336","doi":"https://doi.org/10.21437/interspeech.2020-2357","mag":"3095315336"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2357","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2008.03403","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100693435","display_name":"Ahmed Ali","orcid":"https://orcid.org/0000-0002-9186-7544"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ahmed Ali","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5027442277","display_name":"Steve Renals","orcid":"https://orcid.org/0000-0002-8790-3389"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Steve Renals","raw_affiliation_strings":[],"affiliations":[]}],"institution_assertions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.455,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.531325,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":84,"max":85},"biblio":{"volume":null,"issue":null,"first_page":"616","last_page":"620"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9996,"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":0.9996,"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":0.9919,"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":0.991,"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/word-error-rate","display_name":"Word error rate","score":0.6787486},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.465849}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8032145},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7223503},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6787486},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5392505},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.49989986},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.4885298},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.465849},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4444202},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40939212},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37078768},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.19444326},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12055674},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10497704},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2357","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2008.03403","pdf_url":"https://arxiv.org/pdf/2008.03403","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2008.03403","pdf_url":"https://arxiv.org/pdf/2008.03403","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[{"display_name":"Peace, justice, and strong institutions","score":0.43,"id":"https://metadata.un.org/sdg/16"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4313178214","https://openalex.org/W3093766508","https://openalex.org/W2970653563","https://openalex.org/W2944691285","https://openalex.org/W2914532148","https://openalex.org/W2899717399","https://openalex.org/W2372625757","https://openalex.org/W2349769824","https://openalex.org/W2012393389","https://openalex.org/W1494724239"],"abstract_inverted_index":{"Measuring":[0],"the":[1,17,49,80,115,143,147],"performance":[2],"of":[3],"automatic":[4],"speech":[5,63,69],"recognition":[6,93],"(ASR)":[7],"systems":[8,60,67,75],"requires":[9],"manually":[10],"transcribed":[11],"data":[12],"in":[13,35],"order":[14],"to":[15,47,79,100],"compute":[16],"word":[18],"error":[19,123],"rate":[20],"(WER),":[21],"which":[22],"is":[23,134],"often":[24],"time-consuming":[25],"and":[26,41,73,118],"expensive.":[27],"In":[28],"this":[29],"paper,":[30],"we":[31],"continue":[32],"our":[33,107],"effort":[34],"estimating":[36],"WER":[37,50,104,131,144],"using":[38,61,146],"acoustic,":[39],"lexical":[40],"phonotactic":[42],"features.":[43],"Our":[44],"novel":[45],"approach":[46],"estimate":[48,101],"uses":[51],"a":[52,137],"multistream":[53],"end-to-end":[54],"architecture.":[55],"We":[56],"report":[57],"results":[58,94],"for":[59,74,136],"internal":[62],"decoder":[64,70],"features":[65,71,99],"(glass-box),":[66],"without":[68,76],"(black-box),":[72],"having":[77],"access":[78],"ASR":[81],"system":[82,86,109],"(no-box).":[83],"The":[84,128],"no-box":[85,108],"learns":[87],"joint":[88],"acoustic-lexical":[89],"representation":[90],"from":[91],"phoneme":[92],"along":[95],"with":[96,114],"MFCC":[97],"acoustic":[98],"WER.":[102],"Considering":[103],"per":[105],"sentence,":[106],"achieves":[110],"0.56":[111],"Pearson":[112],"correlation":[113],"reference":[116,148],"evaluation":[117],"0.24":[119],"root":[120],"mean":[121],"square":[122],"(RMSE)":[124],"across":[125],"1,400":[126],"sentences.":[127],"estimated":[129],"overall":[130],"by":[132],"e-WER2":[133],"30.9%":[135],"three":[138],"hours":[139],"test":[140],"set,":[141],"while":[142],"computed":[145],"transcriptions":[149],"was":[150],"28.5%.":[151]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3095315336","counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2}],"updated_date":"2025-01-23T02:34:41.308104","created_date":"2020-11-09"}