{"id":"https://openalex.org/W4224919704","doi":"https://doi.org/10.1109/icassp43922.2022.9747355","title":"Contrastive Siamese Network for Semi-Supervised Speech Recognition","display_name":"Contrastive Siamese Network for Semi-Supervised Speech Recognition","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224919704","doi":"https://doi.org/10.1109/icassp43922.2022.9747355"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747355","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747355","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5025206583","display_name":"Soheil Khorram","orcid":"https://orcid.org/0000-0002-2306-3341"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Soheil Khorram","raw_affiliation_strings":["Google Inc,USA","Google Inc, USA"],"affiliations":[{"raw_affiliation_string":"Google Inc,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100344655","display_name":"Jaeyoung Kim","orcid":"https://orcid.org/0000-0002-4830-0454"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jaeyoung Kim","raw_affiliation_strings":["Google Inc,USA","Google Inc, USA"],"affiliations":[{"raw_affiliation_string":"Google Inc,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101403998","display_name":"Anshuman Tripathi","orcid":"https://orcid.org/0000-0002-4902-3719"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anshuman Tripathi","raw_affiliation_strings":["Google Inc,USA","Google Inc, USA"],"affiliations":[{"raw_affiliation_string":"Google Inc,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086894713","display_name":"Lu Han","orcid":"https://orcid.org/0000-0002-1120-3220"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Han Lu","raw_affiliation_strings":["Google Inc,USA","Google Inc, USA"],"affiliations":[{"raw_affiliation_string":"Google Inc,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115603610","display_name":"Qian Zhang","orcid":"https://orcid.org/0000-0001-5975-9781"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qian Zhang","raw_affiliation_strings":["Google Inc,USA","Google Inc, USA"],"affiliations":[{"raw_affiliation_string":"Google Inc,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108537573","display_name":"Ha\u015fim Sak","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hasim Sak","raw_affiliation_strings":["Google Inc,USA","Google Inc, USA"],"affiliations":[{"raw_affiliation_string":"Google Inc,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5025206583"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":1.3512,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.82444516,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7207","last_page":"7211"},"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":0.9995999932289124,"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/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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/transformer","display_name":"Transformer","score":0.7141861319541931},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6967207789421082},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5795247554779053},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.560482919216156},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5412340760231018},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49726060032844543},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4900254011154175},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42548608779907227},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.42283904552459717},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1887548565864563},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0907115638256073}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7141861319541931},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6967207789421082},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5795247554779053},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.560482919216156},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5412340760231018},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49726060032844543},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4900254011154175},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42548608779907227},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.42283904552459717},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1887548565864563},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0907115638256073},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/icassp43922.2022.9747355","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747355","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1828163288","https://openalex.org/W2152790380","https://openalex.org/W2168510624","https://openalex.org/W2842511635","https://openalex.org/W2883725317","https://openalex.org/W2936774411","https://openalex.org/W2964110616","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W2979476256","https://openalex.org/W2982223350","https://openalex.org/W3005680577","https://openalex.org/W3015265920","https://openalex.org/W3016010032","https://openalex.org/W3016970897","https://openalex.org/W3035060554","https://openalex.org/W3035524453","https://openalex.org/W3036601975","https://openalex.org/W3041561163","https://openalex.org/W3093579165","https://openalex.org/W3097777922","https://openalex.org/W3103934428","https://openalex.org/W3112034174","https://openalex.org/W3171007011","https://openalex.org/W3198608154","https://openalex.org/W4226033575","https://openalex.org/W4297808394","https://openalex.org/W6631190155","https://openalex.org/W6638749077","https://openalex.org/W6682948231","https://openalex.org/W6753000030","https://openalex.org/W6769196770","https://openalex.org/W6774314701","https://openalex.org/W6779326418","https://openalex.org/W6780218876","https://openalex.org/W6784426525","https://openalex.org/W6784614252","https://openalex.org/W6786669483"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W4205302943","https://openalex.org/W2119949815","https://openalex.org/W2561132942","https://openalex.org/W3037446006","https://openalex.org/W2944691285","https://openalex.org/W4287752972","https://openalex.org/W3037482713"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"contrastive":[3,55],"siamese":[4],"(c-siam)":[5],"network,":[6],"an":[7,69],"architecture":[8],"for":[9],"leveraging":[10],"unlabeled":[11],"acoustic":[12],"data":[13,95,101],"in":[14],"speech":[15,28],"recognition.":[16],"c-siam":[17,104,113,125],"is":[18],"the":[19,64,74,85,91,97,135],"first":[20],"network":[21,126],"that":[22,112],"extracts":[23],"high-level":[24],"linguistic":[25],"information":[26],"from":[27],"by":[29],"matching":[30,51],"outputs":[31,52],"of":[32],"two":[33],"identical":[34],"transformer":[35],"encoders.":[36],"It":[37],"contains":[38],"augmented":[39,75],"and":[40,50,96,105],"target":[41,65],"branches":[42],"which":[43],"are":[44],"trained":[45],"by:":[46],"(1)":[47],"masking":[48],"inputs":[49],"with":[53,127,138],"a":[54,59],"loss,":[56],"(2)":[57],"incorporating":[58],"stop":[60],"gradient":[61],"operation":[62],"on":[63,73],"branch,":[66,76],"(3)":[67],"using":[68],"extra":[70],"learnable":[71],"transformation":[72],"(4)":[77],"introducing":[78],"new":[79],"temporal":[80],"augment":[81],"functions":[82],"to":[83,102,134],"prevent":[84],"shortcut":[86],"learning":[87],"problem.":[88],"We":[89],"use":[90],"Libri-light":[92],"60k":[93],"unsupervised":[94],"LibriSpeech":[98],"100hrs/960hrs":[99],"supervised":[100],"compare":[103],"other":[106],"best-performing":[107],"systems.":[108],"Our":[109],"experiments":[110],"show":[111],"provides":[114],"20%":[115],"relative":[116],"word":[117],"error":[118],"rate":[119],"improvement":[120],"over":[121],"wav2vec":[122],"baselines.":[123],"A":[124],"450M":[128],"parameters":[129],"achieves":[130],"competitive":[131],"results":[132],"compared":[133],"state-of-the-art":[136],"networks":[137],"600M":[139],"parameters.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":7}],"updated_date":"2026-02-13T13:36:01.753593","created_date":"2025-10-10T00:00:00"}