{"id":"https://openalex.org/W3143897156","doi":"https://doi.org/10.21437/interspeech.2021-591","title":"Correcting Automated and Manual Speech Transcription Errors Using Warped Language Models","display_name":"Correcting Automated and Manual Speech Transcription Errors Using Warped Language Models","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3143897156","doi":"https://doi.org/10.21437/interspeech.2021-591","mag":"3143897156"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-591","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-591","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2103.14580.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026771837","display_name":"Mahdi Namazifar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mahdi Namazifar","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015450918","display_name":"John Malik","orcid":"https://orcid.org/0000-0002-1776-5531"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"John Malik","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053710007","display_name":"Li Erran Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Li Erran Li","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087941479","display_name":"G\u00f6khan T\u00fcr","orcid":"https://orcid.org/0009-0008-7740-2557"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gokhan Tur","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042930537","display_name":"Dilek Hakkani T\u00fcr","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dilek Hakkani T\u00fcr","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210089985"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2037","last_page":"2041"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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":0.9998999834060669,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8325013518333435},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7771790027618408},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6318529844284058},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6235203742980957},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.61719810962677},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5922396779060364},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.5845611691474915},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5749887228012085},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4923609495162964},{"id":"https://openalex.org/keywords/cache-language-model","display_name":"Cache language model","score":0.48979663848876953},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4789865016937256},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.45708298683166504},{"id":"https://openalex.org/keywords/universal-networking-language","display_name":"Universal Networking Language","score":0.39002084732055664},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.26018857955932617},{"id":"https://openalex.org/keywords/comprehension-approach","display_name":"Comprehension approach","score":0.1922573447227478}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8325013518333435},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7771790027618408},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6318529844284058},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6235203742980957},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.61719810962677},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5922396779060364},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.5845611691474915},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5749887228012085},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4923609495162964},{"id":"https://openalex.org/C39608478","wikidata":"https://www.wikidata.org/wiki/Q5015979","display_name":"Cache language model","level":5,"score":0.48979663848876953},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4789865016937256},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.45708298683166504},{"id":"https://openalex.org/C83479923","wikidata":"https://www.wikidata.org/wiki/Q2063748","display_name":"Universal Networking Language","level":4,"score":0.39002084732055664},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.26018857955932617},{"id":"https://openalex.org/C129353971","wikidata":"https://www.wikidata.org/wiki/Q5156949","display_name":"Comprehension approach","level":3,"score":0.1922573447227478},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2021-591","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-591","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"mag:3143897156","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2103.14580.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}],"best_oa_location":{"id":"mag:3143897156","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2103.14580.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},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7900000214576721,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W85707815","https://openalex.org/W170508173","https://openalex.org/W2107091848","https://openalex.org/W2537374808","https://openalex.org/W2594610113","https://openalex.org/W2892009249","https://openalex.org/W2935886602","https://openalex.org/W2936261307","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2981488681","https://openalex.org/W2981857663","https://openalex.org/W3006390112","https://openalex.org/W3015747801","https://openalex.org/W3016107769","https://openalex.org/W3095498326"],"related_works":["https://openalex.org/W2165835488","https://openalex.org/W2973135063","https://openalex.org/W2402448994","https://openalex.org/W3095498326","https://openalex.org/W2072073255","https://openalex.org/W138635755","https://openalex.org/W2123524045","https://openalex.org/W2111596830","https://openalex.org/W2293858598","https://openalex.org/W2000287213","https://openalex.org/W399167303","https://openalex.org/W1985007624","https://openalex.org/W2384829717","https://openalex.org/W3034931686","https://openalex.org/W2914699162","https://openalex.org/W2950658695","https://openalex.org/W2964309797","https://openalex.org/W1511502193","https://openalex.org/W1989713946","https://openalex.org/W2121522906"],"abstract_inverted_index":{"Masked":[0],"language":[1,6,20,24,46,50,76],"models":[2,21,25,77],"have":[3],"revolutionized":[4],"natural":[5],"processing":[7],"systems":[8],"in":[9,39,101],"the":[10,33,49,53,72],"past":[11],"few":[12],"years.":[13],"A":[14],"recently":[15],"introduced":[16],"generalization":[17],"of":[18,35,44,56,71,74,84,105,111],"masked":[19],"called":[22],"warped":[23,75],"are":[26],"trained":[27],"to":[28,32,52,78,95,98],"be":[29],"more":[30],"robust":[31],"types":[34,55],"errors":[36,57],"that":[37,68,89],"appear":[38],"automatic":[40,107],"or":[41],"manual":[42,109],"transcriptions":[43,83,110],"spoken":[45,85,112],"by":[47],"exposing":[48],"model":[51],"same":[54],"during":[58],"training.":[59],"In":[60],"this":[61],"work":[62],"we":[63],"propose":[64],"a":[65],"novel":[66],"approach":[67,92],"takes":[69],"advantage":[70],"robustness":[73],"transcription":[79],"noise":[80],"for":[81],"correcting":[82],"language.":[86,113],"We":[87],"show":[88],"our":[90],"proposed":[91],"is":[93],"able":[94],"achieve":[96],"up":[97],"10%":[99],"reduction":[100],"word":[102],"error":[103],"rates":[104],"both":[106],"and":[108]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}