{"id":"https://openalex.org/W4319862269","doi":"https://doi.org/10.1109/slt54892.2023.10022448","title":"Improving Semi-Supervised End-To-End Automatic Speech Recognition Using Cyclegan and Inter-Domain Losses","display_name":"Improving Semi-Supervised End-To-End Automatic Speech Recognition Using Cyclegan and Inter-Domain Losses","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862269","doi":"https://doi.org/10.1109/slt54892.2023.10022448"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10022448","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10022448","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102495766","display_name":"Chia-Yu Li","orcid":null},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Chia-Yu Li","raw_affiliation_strings":["Institute for Natural Language Processing (IMS), University of Stuttgart,Germany","Institute for Natural Language Processing (IMS), University of Stuttgart, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Natural Language Processing (IMS), University of Stuttgart,Germany","institution_ids":["https://openalex.org/I100066346"]},{"raw_affiliation_string":"Institute for Natural Language Processing (IMS), University of Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020700841","display_name":"Ngoc Thang Vu","orcid":"https://orcid.org/0000-0001-7893-9147"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ngoc Thang Vu","raw_affiliation_strings":["Institute for Natural Language Processing (IMS), University of Stuttgart,Germany","Institute for Natural Language Processing (IMS), University of Stuttgart, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Natural Language Processing (IMS), University of Stuttgart,Germany","institution_ids":["https://openalex.org/I100066346"]},{"raw_affiliation_string":"Institute for Natural Language Processing (IMS), University of Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I100066346"],"apc_list":null,"apc_paid":null,"fwci":0.4356,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.54373105,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"822","last_page":"829"},"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/T11309","display_name":"Music and Audio Processing","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9962999820709229,"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":0.770814061164856},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6315270662307739},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6267006397247314},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.621375322341919},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6151598691940308},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5918847322463989},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5661141276359558},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46619170904159546},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44949623942375183},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4224790334701538},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3866494596004486},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11763349175453186}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.770814061164856},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6315270662307739},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6267006397247314},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.621375322341919},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6151598691940308},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5918847322463989},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5661141276359558},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46619170904159546},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44949623942375183},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4224790334701538},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3866494596004486},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11763349175453186},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10022448","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10022448","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1586532344","https://openalex.org/W1686810756","https://openalex.org/W1922655562","https://openalex.org/W2100495367","https://openalex.org/W2102113734","https://openalex.org/W2133564696","https://openalex.org/W2187089797","https://openalex.org/W2193413348","https://openalex.org/W2327501763","https://openalex.org/W2404126548","https://openalex.org/W2514969556","https://openalex.org/W2526425061","https://openalex.org/W2530876040","https://openalex.org/W2545177271","https://openalex.org/W2608712415","https://openalex.org/W2750499125","https://openalex.org/W2766219058","https://openalex.org/W2883586237","https://openalex.org/W2889213362","https://openalex.org/W2962699523","https://openalex.org/W2962780374","https://openalex.org/W2962793481","https://openalex.org/W2962824887","https://openalex.org/W2962826786","https://openalex.org/W2962947361","https://openalex.org/W2963211739","https://openalex.org/W2963739817","https://openalex.org/W2964012862","https://openalex.org/W2972889948","https://openalex.org/W4298393544","https://openalex.org/W4320013936","https://openalex.org/W6623517193","https://openalex.org/W6635078382","https://openalex.org/W6637373629","https://openalex.org/W6640090968","https://openalex.org/W6656414902","https://openalex.org/W6675365184","https://openalex.org/W6679434410","https://openalex.org/W6687566353","https://openalex.org/W6688325169","https://openalex.org/W6734074887","https://openalex.org/W6741328424","https://openalex.org/W6743440867","https://openalex.org/W6745388339","https://openalex.org/W6745740328","https://openalex.org/W6761860026"],"related_works":["https://openalex.org/W3179968364","https://openalex.org/W2393609567","https://openalex.org/W2369369044","https://openalex.org/W1503216044","https://openalex.org/W2354143083","https://openalex.org/W2372906645","https://openalex.org/W4319998713","https://openalex.org/W2366269494","https://openalex.org/W2353650902","https://openalex.org/W2347884623"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,33],"novel":[3],"method":[4],"that":[5],"combines":[6],"CycleGAN":[7,36,86],"and":[8,29,40,85,95,98,111,123],"inter-domain":[9,83],"losses":[10],"for":[11],"semi-supervised":[12],"end-to-end":[13,68],"automatic":[14],"speech":[15,28,94],"recognition.":[16],"Inter-domain":[17],"loss":[18,39,44,84],"targets":[19],"the":[20,41,50,79,101,108,121,124],"extraction":[21],"of":[22,27,49,92],"an":[23],"intermediate":[24],"shared":[25,34,90],"representation":[26,91],"text":[30,96],"inputs":[31,97],"using":[32],"network.":[35],"uses":[37],"cycle-consistent":[38],"identity":[42],"mapping":[43],"to":[45,58,66,87],"preserve":[46],"relevant":[47],"characteristics":[48],"input":[51],"feature":[52],"after":[53],"converting":[54],"from":[55,81],"one":[56],"domain":[57],"another.":[59],"As":[60],"such,":[61],"both":[62,82],"approaches":[63],"are":[64],"suitable":[65],"train":[67],"models":[69],"on":[70,107,126],"unpaired":[71,93],"speech-text":[72],"inputs.":[73],"In":[74],"this":[75],"paper,":[76],"we":[77],"exploit":[78],"advantages":[80],"achieve":[88],"better":[89],"thus":[99],"improve":[100],"speech-to-text":[102],"mapping.":[103],"Our":[104],"experimental":[105],"results":[106,125],"WSJ":[109],"eval92":[110],"Voxforge":[112],"(non":[113],"English)":[114],"show$8\\sim":[115],"8.5\\%$character":[116],"error":[117],"rate":[118],"reduction":[119],"over":[120],"baseline,":[122],"LibriSpeech":[127],"test_clean":[128],"also":[129],"show":[130],"noticeable":[131],"improvement.":[132]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}