{"id":"https://openalex.org/W4406461254","doi":"https://doi.org/10.1109/slt61566.2024.10832230","title":"Transducer Consistency Regularization For Speech to Text Applications","display_name":"Transducer Consistency Regularization For Speech to Text Applications","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461254","doi":"https://doi.org/10.1109/slt61566.2024.10832230"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832230","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832230","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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/A5111024455","display_name":"Cindy Tseng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]},{"id":"https://openalex.org/I4210133173","display_name":"Research!America (United States)","ror":"https://ror.org/044pgyv50","country_code":"US","type":"company","lineage":["https://openalex.org/I4210133173"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cindy Tseng","raw_affiliation_strings":["Samsung Research America,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research America,USA","institution_ids":["https://openalex.org/I4210101778","https://openalex.org/I4210133173"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101926294","display_name":"Yun Tang","orcid":"https://orcid.org/0000-0002-4075-5227"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]},{"id":"https://openalex.org/I4210133173","display_name":"Research!America (United States)","ror":"https://ror.org/044pgyv50","country_code":"US","type":"company","lineage":["https://openalex.org/I4210133173"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yun Tang","raw_affiliation_strings":["Samsung Research America,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research America,USA","institution_ids":["https://openalex.org/I4210101778","https://openalex.org/I4210133173"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075101547","display_name":"Vijendra Raj Apsingekar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]},{"id":"https://openalex.org/I4210133173","display_name":"Research!America (United States)","ror":"https://ror.org/044pgyv50","country_code":"US","type":"company","lineage":["https://openalex.org/I4210133173"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vijendra Raj Apsingekar","raw_affiliation_strings":["Samsung Research America,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research America,USA","institution_ids":["https://openalex.org/I4210101778","https://openalex.org/I4210133173"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"110","last_page":"117"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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":0.9922000169754028,"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/regularization","display_name":"Regularization (linguistics)","score":0.7297549247741699},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7182415127754211},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6372726559638977},{"id":"https://openalex.org/keywords/transducer","display_name":"Transducer","score":0.559867262840271},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5266211628913879},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4577542543411255},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4349757134914398},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.17476814985275269},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08194506168365479}],"concepts":[{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.7297549247741699},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7182415127754211},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6372726559638977},{"id":"https://openalex.org/C56318395","wikidata":"https://www.wikidata.org/wiki/Q215928","display_name":"Transducer","level":2,"score":0.559867262840271},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5266211628913879},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4577542543411255},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4349757134914398},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.17476814985275269},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08194506168365479}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832230","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832230","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2095705004","https://openalex.org/W2908510526","https://openalex.org/W2936774411","https://openalex.org/W2950651087","https://openalex.org/W2962369866","https://openalex.org/W2963250244","https://openalex.org/W2964159205","https://openalex.org/W2974231335","https://openalex.org/W3005680577","https://openalex.org/W3008898571","https://openalex.org/W3015737168","https://openalex.org/W3016010032","https://openalex.org/W3028382961","https://openalex.org/W3095311338","https://openalex.org/W3096888553","https://openalex.org/W3097777922","https://openalex.org/W3162249256","https://openalex.org/W3162649911","https://openalex.org/W3162665866","https://openalex.org/W3174864715","https://openalex.org/W3211278025","https://openalex.org/W3213993043","https://openalex.org/W4224137820","https://openalex.org/W4283700324","https://openalex.org/W4288088457","https://openalex.org/W4296069270","https://openalex.org/W4297727296","https://openalex.org/W4372259874","https://openalex.org/W4385245566","https://openalex.org/W4385571513","https://openalex.org/W4391021739","https://openalex.org/W4401043086","https://openalex.org/W6674330103","https://openalex.org/W6757817989","https://openalex.org/W6765939562","https://openalex.org/W6767671539","https://openalex.org/W6769806307","https://openalex.org/W6774314701","https://openalex.org/W6777859140","https://openalex.org/W6790121257","https://openalex.org/W6797110910","https://openalex.org/W6857062747"],"related_works":["https://openalex.org/W2012283803","https://openalex.org/W4384820447","https://openalex.org/W2072454424","https://openalex.org/W2117438306","https://openalex.org/W2185942010","https://openalex.org/W2260725127","https://openalex.org/W2004297762","https://openalex.org/W1992056405","https://openalex.org/W1966826629","https://openalex.org/W767846903"],"abstract_inverted_index":{"Consistency":[0,100],"regularization":[1,46,105,165],"is":[2,40,69,160],"a":[3,103,180],"commonly":[4],"used":[5],"practice":[6],"to":[7,11,43,59,89,119,133,145,150,162],"encourage":[8],"the":[9,48,60,71,76,83,86,90,126,151,157,184],"model":[10,21,91,152],"generate":[12],"consistent":[13],"representation":[14],"from":[15,70],"distorted":[16],"input":[17],"features":[18],"and":[19,63,80,117,124,167],"improve":[20],"generalization.":[22],"It":[23],"shows":[24],"significant":[25],"improvement":[26],"on":[27,137,183],"various":[28],"speech":[29,56],"applications":[30,57],"that":[31],"are":[32,52],"optimized":[33],"with":[34,179],"cross":[35],"entropy":[36],"criterion.":[37],"However,":[38],"it":[39],"not":[41,81],"straightforward":[42],"apply":[44,111],"consistency":[45,104,164],"for":[47,55,107],"transducer-based":[49],"approaches,":[50],"which":[51],"widely":[53],"adopted":[54],"due":[58],"competitive":[61],"performance":[62],"streaming":[64],"characteristic.":[65],"The":[66],"main":[67],"challenge":[68],"vast":[72],"alignment":[73],"space":[74,87],"of":[75],"transducer":[77,108,138],"optimization":[78,92],"criterion":[79],"all":[82],"alignments":[84,143,147],"within":[85],"contribute":[88,149],"equally.":[93],"In":[94],"this":[95],"study,":[96],"we":[97],"present":[98],"Transducer":[99],"Regularization":[101],"(TCR),":[102],"method":[106,159],"models.":[109],"We":[110,129],"distortions":[112],"such":[113],"as":[114],"spec":[115],"augmentation":[116],"dropout":[118],"create":[120],"different":[121,135],"data":[122],"views":[123],"minimize":[125],"distribution":[127],"difference.":[128],"utilize":[130],"occupational":[131],"probabilities":[132],"give":[134],"weights":[136],"output":[139],"distributions,":[140],"thus":[141],"only":[142],"close":[144],"oracle":[146],"would":[148],"learning.":[153],"Our":[154],"experiments":[155],"show":[156],"proposed":[158],"superior":[161],"other":[163],"implementations":[166],"could":[168],"effectively":[169],"reduce":[170],"word":[171],"error":[172],"rate":[173],"(WER)":[174],"by":[175],"4.3%":[176],"relatively":[177],"comparing":[178],"strong":[181],"baseline":[182],"Librispeech":[185],"dataset.":[186]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}