{"id":"https://openalex.org/W3205080563","doi":"https://doi.org/10.1109/icassp43922.2022.9746249","title":"Improving Pseudo-Label Training For End-To-End Speech Recognition Using Gradient Mask","display_name":"Improving Pseudo-Label Training For End-To-End Speech Recognition Using Gradient Mask","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3205080563","doi":"https://doi.org/10.1109/icassp43922.2022.9746249","mag":"3205080563"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746249","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746249","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/A5109397773","display_name":"Shaoshi Ling","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shaoshi Ling","raw_affiliation_strings":["Bytedance AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance AI Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022877637","display_name":"Chen Shen","orcid":"https://orcid.org/0000-0002-7534-0830"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Shen","raw_affiliation_strings":["Bytedance AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance AI Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052057753","display_name":"Meng Cai","orcid":"https://orcid.org/0000-0002-0711-5949"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng Cai","raw_affiliation_strings":["Bytedance AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance AI Lab","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110851569","display_name":"Zejun Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zejun Ma","raw_affiliation_strings":["Bytedance AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance AI Lab","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8435,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.72922262,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"8397","last_page":"8401"},"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":0.9994999766349792,"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":0.9986000061035156,"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":0.7757810354232788},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6620703339576721},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6209720373153687},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5802944302558899},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5426599979400635},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46773844957351685},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4402328431606293},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4191695749759674},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4110337793827057},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3365488648414612},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.28335049748420715},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.05363062024116516}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7757810354232788},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6620703339576721},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6209720373153687},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5802944302558899},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5426599979400635},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46773844957351685},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4402328431606293},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4191695749759674},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4110337793827057},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3365488648414612},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.28335049748420715},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.05363062024116516},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/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},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746249","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746249","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":[{"display_name":"Quality Education","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1828163288","https://openalex.org/W1993660824","https://openalex.org/W2127141656","https://openalex.org/W2167460663","https://openalex.org/W2327501763","https://openalex.org/W2512655038","https://openalex.org/W2545319977","https://openalex.org/W2802248956","https://openalex.org/W2889213362","https://openalex.org/W2896457183","https://openalex.org/W2928408492","https://openalex.org/W2936774411","https://openalex.org/W2962784628","https://openalex.org/W2962907457","https://openalex.org/W2963341956","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W2982223350","https://openalex.org/W3004534439","https://openalex.org/W3015265920","https://openalex.org/W3015315932","https://openalex.org/W3015522062","https://openalex.org/W3024182269","https://openalex.org/W3025165719","https://openalex.org/W3026041220","https://openalex.org/W3027083471","https://openalex.org/W3036601975","https://openalex.org/W3041561163","https://openalex.org/W3042609801","https://openalex.org/W3093788532","https://openalex.org/W3096338464","https://openalex.org/W3097777922","https://openalex.org/W3099782249","https://openalex.org/W3103005696","https://openalex.org/W3112034174","https://openalex.org/W3121299949","https://openalex.org/W3160235762","https://openalex.org/W3167207712","https://openalex.org/W3169320628","https://openalex.org/W3178203035","https://openalex.org/W3197223534","https://openalex.org/W3209059054","https://openalex.org/W4287716221","https://openalex.org/W6629717138","https://openalex.org/W6631362777","https://openalex.org/W6638575559","https://openalex.org/W6638749077","https://openalex.org/W6755207826","https://openalex.org/W6780218876","https://openalex.org/W6780361010","https://openalex.org/W6780530918","https://openalex.org/W6784436999","https://openalex.org/W6786669483","https://openalex.org/W6788335241","https://openalex.org/W6797992114"],"related_works":["https://openalex.org/W2044408773","https://openalex.org/W2130717063","https://openalex.org/W4383605217","https://openalex.org/W2533508831","https://openalex.org/W2742699532","https://openalex.org/W4281389974","https://openalex.org/W1911859126","https://openalex.org/W2158598479","https://openalex.org/W1964178275","https://openalex.org/W2325482719"],"abstract_inverted_index":{"In":[0,18,78],"the":[1,42,47,56,63,82,86,105],"recent":[2],"trend":[3],"of":[4],"semi-supervised":[5,80,102],"speech":[6,32,57],"recognition,":[7],"both":[8],"self-supervised":[9],"representation":[10,70],"learning":[11],"and":[12,71,93],"pseudo-labeling":[13],"have":[14],"shown":[15],"promising":[16],"results.":[17],"this":[19],"paper,":[20],"we":[21,40],"propose":[22],"a":[23],"novel":[24],"approach":[25],"to":[26,45,60,66,75],"combine":[27],"their":[28],"ideas":[29],"for":[30],"end-to-end":[31],"recognition":[33,58],"model.":[34],"Without":[35],"any":[36],"extra":[37],"loss":[38],"function,":[39],"utilize":[41],"Gradient":[43],"Mask":[44],"optimize":[46],"model":[48,59],"when":[49,89],"training":[50,73,90],"on":[51,91,104],"pseudo-label.":[52],"This":[53],"method":[54,83,95],"forces":[55],"predict":[61],"from":[62],"masked":[64],"in-put":[65],"learn":[67],"strong":[68],"acoustic":[69],"make":[72],"robust":[74],"label":[76],"noise.":[77],"our":[79,94],"experiments,":[81],"can":[84],"improve":[85],"model\u2019s":[87],"performance":[88],"pseudo-label":[92],"achieved":[96],"competitive":[97],"results":[98],"comparing":[99],"with":[100],"other":[101],"approaches":[103],"Librispeech":[106],"100":[107],"hours":[108],"experiments.":[109]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}