{"id":"https://openalex.org/W4402402732","doi":"https://doi.org/10.1109/icasspw62465.2024.10669910","title":"Word-Level ASR Quality Estimation for Efficient Corpus Sampling and Post-Editing Through Analyzing Attentions of a Reference-Free Metric","display_name":"Word-Level ASR Quality Estimation for Efficient Corpus Sampling and Post-Editing Through Analyzing Attentions of a Reference-Free Metric","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4402402732","doi":"https://doi.org/10.1109/icasspw62465.2024.10669910"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw62465.2024.10669910","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icasspw62465.2024.10669910","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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/A5065820437","display_name":"Golara Javadi","orcid":"https://orcid.org/0000-0002-8945-1101"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Golara Javadi","raw_affiliation_strings":["AiXplain Inc.,Los Gatos,CA,USA"],"affiliations":[{"raw_affiliation_string":"AiXplain Inc.,Los Gatos,CA,USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033353054","display_name":"Kamer Ali Y\u00fcksel","orcid":"https://orcid.org/0000-0002-9404-8472"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kamer Ali Yuksel","raw_affiliation_strings":["AiXplain Inc.,Los Gatos,CA,USA"],"affiliations":[{"raw_affiliation_string":"AiXplain Inc.,Los Gatos,CA,USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005673540","display_name":"Yunsu Kim","orcid":"https://orcid.org/0000-0002-1375-005X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunsu Kim","raw_affiliation_strings":["AiXplain Inc.,Los Gatos,CA,USA"],"affiliations":[{"raw_affiliation_string":"AiXplain Inc.,Los Gatos,CA,USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101930005","display_name":"Thiago Castro Ferreira","orcid":"https://orcid.org/0000-0003-0200-3646"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thiago Castro Ferreira","raw_affiliation_strings":["AiXplain Inc.,Los Gatos,CA,USA"],"affiliations":[{"raw_affiliation_string":"AiXplain Inc.,Los Gatos,CA,USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073237528","display_name":"Mohamed Al-Badrashiny","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohamed Al-Badrashiny","raw_affiliation_strings":["AiXplain Inc.,Los Gatos,CA,USA"],"affiliations":[{"raw_affiliation_string":"AiXplain Inc.,Los Gatos,CA,USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5065820437"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13104703,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"863","last_page":"867"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9986000061035156,"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":0.8150253295898438},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.7215346097946167},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7193830013275146},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5559934973716736},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5131393074989319},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.509725034236908},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4815566837787628},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.46360859274864197},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.42817550897598267},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.42623692750930786},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08552640676498413},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.07021021842956543},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06219378113746643}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8150253295898438},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.7215346097946167},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7193830013275146},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5559934973716736},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5131393074989319},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.509725034236908},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4815566837787628},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.46360859274864197},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.42817550897598267},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42623692750930786},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08552640676498413},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.07021021842956543},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06219378113746643},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw62465.2024.10669910","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icasspw62465.2024.10669910","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2516809705","https://openalex.org/W2946794439","https://openalex.org/W2970820321","https://openalex.org/W3030437843","https://openalex.org/W3097777922","https://openalex.org/W3099143320","https://openalex.org/W3101155149","https://openalex.org/W3174544005","https://openalex.org/W3198765931","https://openalex.org/W3211986039","https://openalex.org/W3212319100","https://openalex.org/W4372266909","https://openalex.org/W4385478146","https://openalex.org/W4385572322","https://openalex.org/W4385823237","https://openalex.org/W6785177581","https://openalex.org/W6847363464","https://openalex.org/W6853565822"],"related_works":["https://openalex.org/W2576994247","https://openalex.org/W2608353378","https://openalex.org/W4249206767","https://openalex.org/W2563559453","https://openalex.org/W2382330008","https://openalex.org/W1519970947","https://openalex.org/W4243860260","https://openalex.org/W1569283511","https://openalex.org/W4383503847","https://openalex.org/W2133478886"],"abstract_inverted_index":{"In":[0],"the":[1,8,57,60,85,90,164,167],"realm":[2],"of":[3,31,59,87,105,166,172],"automatic":[4],"speech":[5],"recognition":[6],"(ASR),":[7],"quest":[9],"for":[10,126,146,154],"models":[11],"that":[12,139],"not":[13,142],"only":[14],"perform":[15],"with":[16,99],"high":[17],"accuracy":[18],"but":[19,149],"also":[20,82,150],"offer":[21],"transparency":[22],"in":[23,50,69,76,89,96,129],"their":[24],"decision-making":[25],"processes":[26],"is":[27,36,141],"crucial.":[28],"The":[29,80,102,136],"potential":[30],"quality":[32],"estimation":[33],"(QE)":[34],"metrics":[35],"introduced":[37],"and":[38,55,119,132,160],"evaluated":[39],"as":[40],"a":[41,144,151],"novel":[42],"tool":[43,145],"to":[44,73,84,112],"enhance":[45],"explainable":[46],"artificial":[47],"intelligence":[48],"(XAI)":[49],"ASR":[51,78,134,156],"systems.":[52],"Through":[53],"experiments":[54],"analyses,":[56],"capabilities":[58],"NoRefER":[61,88,106,140],"(No":[62],"Reference":[63],"Error":[64],"Rate)":[65],"metric":[66],"are":[67,107,175],"explored":[68],"identifying":[70],"word-level":[71],"errors":[72],"aid":[74],"post-editors":[75],"refining":[77],"hypotheses.":[79],"investigation":[81],"extends":[83],"utility":[86],"corpus-building":[91],"process,":[92],"demonstrating":[93],"its":[94,110],"effectiveness":[95],"augmenting":[97],"datasets":[98],"insightful":[100],"annotations.":[101],"diagnostic":[103],"aspects":[104],"examined,":[108],"revealing":[109],"ability":[111],"provide":[113],"valuable":[114],"insights":[115],"into":[116],"model":[117],"behaviors":[118],"decision":[120],"patterns.":[121],"This":[122],"has":[123],"proven":[124],"beneficial":[125],"prioritizing":[127],"hypotheses":[128],"post-editing":[130],"workflows":[131],"fine-tuning":[133],"models.":[135],"findings":[137],"suggest":[138],"merely":[143],"error":[147],"detection":[148],"comprehensive":[152],"framework":[153],"enhancing":[155],"systems\u2019":[157],"transparency,":[158],"efficiency,":[159],"effectiveness.":[161],"To":[162],"ensure":[163],"reproducibility":[165],"results,":[168],"all":[169],"source":[170],"codes":[171],"this":[173],"study":[174],"made":[176],"publicly":[177],"available":[178],"<sup":[179],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[180],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>.":[181]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}