{"id":"https://openalex.org/W4223945715","doi":"https://doi.org/10.1109/icassp43922.2022.9746668","title":"Self-Critical Sequence Training for Automatic Speech Recognition","display_name":"Self-Critical Sequence Training for Automatic Speech Recognition","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4223945715","doi":"https://doi.org/10.1109/icassp43922.2022.9746668"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746668","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746668","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":"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/A5100418563","display_name":"Chen Chen","orcid":"https://orcid.org/0000-0003-3498-2527"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chen Chen","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University,Singapore","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074544822","display_name":"Yu\u2010Chen Hu","orcid":"https://orcid.org/0000-0002-5055-3645"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yuchen Hu","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University,Singapore","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001511287","display_name":"Nana Hou","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Nana Hou","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University,Singapore","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110451381","display_name":"Xiaofeng Qi","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xiaofeng Qi","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University,Singapore","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023152132","display_name":"Heqing Zou","orcid":"https://orcid.org/0000-0003-0038-2822"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Heqing Zou","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University,Singapore","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University,Singapore","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3688","last_page":"3692"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"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":0.9977999925613403,"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":0.7383043766021729},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6285650730133057},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5696118474006653},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5489858984947205},{"id":"https://openalex.org/keywords/forcing","display_name":"Forcing (mathematics)","score":0.5469551086425781},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5411447882652283},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5317460298538208},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.49817728996276855},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.4387736916542053},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4229412376880646},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3805309534072876},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11855977773666382},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10841560363769531}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7383043766021729},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6285650730133057},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5696118474006653},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5489858984947205},{"id":"https://openalex.org/C197115733","wikidata":"https://www.wikidata.org/wiki/Q1003136","display_name":"Forcing (mathematics)","level":2,"score":0.5469551086425781},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5411447882652283},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5317460298538208},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.49817728996276855},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.4387736916542053},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4229412376880646},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3805309534072876},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11855977773666382},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10841560363769531},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746668","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746668","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":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6800000071525574}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2016589492","https://openalex.org/W2119717200","https://openalex.org/W2130942839","https://openalex.org/W2143612262","https://openalex.org/W2176263492","https://openalex.org/W2250499536","https://openalex.org/W2327501763","https://openalex.org/W2526425061","https://openalex.org/W2809161641","https://openalex.org/W2941814890","https://openalex.org/W2962765220","https://openalex.org/W2963084599","https://openalex.org/W2963144852","https://openalex.org/W2963250244","https://openalex.org/W2963747784","https://openalex.org/W3094979069","https://openalex.org/W3095697114","https://openalex.org/W3097777922","https://openalex.org/W3186546663","https://openalex.org/W4214717370","https://openalex.org/W4385245566","https://openalex.org/W6679436768","https://openalex.org/W6685322675","https://openalex.org/W6691605950","https://openalex.org/W6738974909","https://openalex.org/W6739901393","https://openalex.org/W6752627816","https://openalex.org/W6761563299","https://openalex.org/W6770425081","https://openalex.org/W6777337586","https://openalex.org/W6799474351"],"related_works":["https://openalex.org/W2971214053","https://openalex.org/W2949231297","https://openalex.org/W2060606417","https://openalex.org/W2146197305","https://openalex.org/W2134950286","https://openalex.org/W2102131353","https://openalex.org/W3108423942","https://openalex.org/W3171409398","https://openalex.org/W1968425736","https://openalex.org/W2118534475"],"abstract_inverted_index":{"Although":[0],"automatic":[1],"speech":[2,151],"recognition":[3],"(ASR)":[4],"task":[5],"has":[6,72],"gained":[7],"remarkable":[8],"success":[9],"by":[10,48],"sequence-to-sequence":[11],"models,":[12],"there":[13],"are":[14],"two":[15],"main":[16],"mismatches":[17],"between":[18],"its":[19,77,140],"training":[20,41,93,98,122],"and":[21,124,133,149,153,164],"testing":[22,104],"that":[23,70,157],"might":[24],"lead":[25],"to":[26,36,60,76,95,102,119,139],"performance":[27,45],"degradation:":[28],"1)":[29],"The":[30,56],"typically":[31],"used":[32],"cross-entropy":[33],"criterion":[34,123],"aims":[35],"maximize":[37],"log-likelihood":[38],"of":[39,173],"the":[40,44,61,97,103,121,129,135,154,158,169],"data,":[42],"while":[43],"is":[46],"evaluated":[47],"word":[49],"error":[50],"rate":[51],"(WER),":[52],"not":[53],"log-likelihood;":[54],"2)":[55],"teacher-forcing":[57,132],"method":[58,89],"leads":[59],"dependence":[62],"on":[63,131,146],"ground":[64],"truth":[65],"during":[66],"training,":[67],"which":[68],"means":[69],"model":[71,136],"never":[73],"been":[74],"exposed":[75],"own":[78],"prediction":[79],"before":[80],"testing.":[81],"In":[82],"this":[83],"paper,":[84],"we":[85],"propose":[86],"an":[87],"optimization":[88],"called":[90],"self-critical":[91],"sequence":[92],"(SCST)":[94],"make":[96],"procedure":[99],"much":[100],"closer":[101],"phase.":[105],"As":[106],"a":[107,115],"reinforcement":[108],"learning":[109],"(RL)":[110],"based":[111],"method,":[112],"SCST":[113,160],"utilizes":[114],"customized":[116],"reward":[117],"function":[118],"associate":[120],"WER.":[125,174],"Furthermore,":[126],"it":[127],"removes":[128],"reliance":[130],"harmonizes":[134],"with":[137],"respect":[138],"inference":[141],"procedure.":[142],"We":[143],"conducted":[144],"experiments":[145],"both":[147],"clean":[148],"noisy":[150],"datasets,":[152],"results":[155],"show":[156],"proposed":[159],"respectively":[161],"achieves":[162],"8.7%":[163],"7.8%":[165],"relative":[166],"improvements":[167],"over":[168],"baseline":[170],"in":[171],"terms":[172]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}