{"id":"https://openalex.org/W4319323883","doi":"https://doi.org/10.1109/slt54892.2023.10022676","title":"Guided Contrastive Self-Supervised Pre-Training for Automatic Speech Recognition","display_name":"Guided Contrastive Self-Supervised Pre-Training for Automatic Speech Recognition","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319323883","doi":"https://doi.org/10.1109/slt54892.2023.10022676"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10022676","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10022676","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/A5013650472","display_name":"Aparna Khare","orcid":"https://orcid.org/0000-0001-7151-3055"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aparna Khare","raw_affiliation_strings":["Amazon Alexa,USA","Amazon Alexa, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060740546","display_name":"Minhua Wu","orcid":"https://orcid.org/0000-0001-9798-2984"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minhua Wu","raw_affiliation_strings":["Amazon Alexa,USA","Amazon Alexa, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045247662","display_name":"Saurabhchand Bhati","orcid":"https://orcid.org/0000-0001-6477-3895"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saurabhchand Bhati","raw_affiliation_strings":["Amazon Alexa,USA","Amazon Alexa, USA","Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa, USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012153296","display_name":"Jasha Droppo","orcid":"https://orcid.org/0000-0001-6097-0090"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jasha Droppo","raw_affiliation_strings":["Amazon Alexa,USA","Amazon Alexa, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086411272","display_name":"Roland Maas","orcid":"https://orcid.org/0000-0003-0567-5640"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roland Maas","raw_affiliation_strings":["Amazon Alexa,USA","Amazon Alexa, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa, USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2057,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.36165249,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"174","last_page":"181"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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":0.9983999729156494,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7891443967819214},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.701425313949585},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6793445348739624},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6234971284866333},{"id":"https://openalex.org/keywords/predictive-coding","display_name":"Predictive coding","score":0.6209084987640381},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5478843450546265},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.5373353958129883},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.5314361453056335},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5062565207481384},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.463156133890152},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4407196044921875},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4365992844104767},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36569270491600037},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11202937364578247},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10867932438850403}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7891443967819214},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.701425313949585},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6793445348739624},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6234971284866333},{"id":"https://openalex.org/C2778061373","wikidata":"https://www.wikidata.org/wiki/Q1315146","display_name":"Predictive coding","level":3,"score":0.6209084987640381},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5478843450546265},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.5373353958129883},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.5314361453056335},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5062565207481384},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.463156133890152},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4407196044921875},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4365992844104767},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36569270491600037},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11202937364578247},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10867932438850403},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10022676","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10022676","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":[{"id":"https://metadata.un.org/sdg/4","score":0.6600000262260437,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1828163288","https://openalex.org/W2127141656","https://openalex.org/W2187089797","https://openalex.org/W2520160253","https://openalex.org/W2842511635","https://openalex.org/W2951974815","https://openalex.org/W2962739339","https://openalex.org/W2963250244","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W2982223350","https://openalex.org/W2995181338","https://openalex.org/W3015265920","https://openalex.org/W3024182269","https://openalex.org/W3036601975","https://openalex.org/W3100270690","https://openalex.org/W3160235762","https://openalex.org/W3178203035","https://openalex.org/W3209059054","https://openalex.org/W3212799896","https://openalex.org/W4226033575","https://openalex.org/W4283324001","https://openalex.org/W4297808394","https://openalex.org/W6638749077","https://openalex.org/W6682948231","https://openalex.org/W6727336983","https://openalex.org/W6755207826","https://openalex.org/W6769196770","https://openalex.org/W6780218876","https://openalex.org/W6788335241","https://openalex.org/W6797992114"],"related_works":["https://openalex.org/W1566315437","https://openalex.org/W4221142855","https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W2050138804","https://openalex.org/W767271433","https://openalex.org/W4290708361","https://openalex.org/W2129812225","https://openalex.org/W2523799048","https://openalex.org/W2155620340"],"abstract_inverted_index":{"Contrastive":[0,50],"Predictive":[1,51],"Coding":[2,52],"(CPC)":[3],"is":[4],"a":[5,22,43,64],"representation":[6],"learning":[7],"method":[8,56,84,94],"that":[9],"maximizes":[10,57],"the":[11,19,32,58,68,71,103,115],"mutual":[12,59],"information":[13,60],"between":[14,61],"intermediate":[15],"latent":[16],"representations":[17,62],"and":[18,67,91,111,118,135],"output":[20,69],"of":[21,34,46,70],"given":[23],"model.":[24,40],"It":[25],"can":[26],"be":[27],"used":[28],"to":[29,124],"effectively":[30],"initialize":[31],"encoder":[33],"an":[35],"Automatic":[36],"Speech":[37],"Recognition":[38],"(ASR)":[39],"We":[41,81],"present":[42],"novel":[44],"modification":[45],"CPC":[47,96,129],"called":[48],"Guided":[49],"(GCPC).":[53],"Our":[54,93],"proposed":[55],"from":[63,126],"prior-knowledge":[65],"model":[66,72],"being":[73],"pre-trained,":[74],"allowing":[75],"prior":[76],"knowledge":[77],"injection":[78],"during":[79],"pre-training.":[80],"validate":[82],"our":[83],"on":[85,98,114],"3":[86],"ASR":[87],"tasks:":[88],"German,":[89,116],"French":[90,117],"English.":[92],"outperforms":[95],"pre-training":[97,130],"all":[99],"three":[100],"datasets,":[101],"reducing":[102],"Word":[104],"Error":[105],"Rate":[106],"(WER)":[107],"by":[108],"4.44%,":[109],"6.55%":[110],"15.43%":[112],"relative":[113,137],"English":[119],"(Librispeech)":[120],"tasks":[121],"respectively,":[122],"compared":[123],"training":[125],"scratch,":[127],"while":[128],"only":[131],"brings":[132],"2.96%,":[133],"1.01%":[134],"14.39%":[136],"WER":[138],"reduction":[139],"respectively.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2023-02-08T00:00:00"}