{"id":"https://openalex.org/W4319586927","doi":"https://doi.org/10.1109/dsaa54385.2022.10032360","title":"Adaptive Sparse and Monotonic Attention for Transformer-based Automatic Speech Recognition","display_name":"Adaptive Sparse and Monotonic Attention for Transformer-based Automatic Speech Recognition","publication_year":2022,"publication_date":"2022-10-13","ids":{"openalex":"https://openalex.org/W4319586927","doi":"https://doi.org/10.1109/dsaa54385.2022.10032360"},"language":"en","primary_location":{"id":"doi:10.1109/dsaa54385.2022.10032360","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsaa54385.2022.10032360","pdf_url":null,"source":{"id":"https://openalex.org/S4363608340","display_name":"2022 IEEE 9th International Conference on Data Science and Advanced Analytics (DSAA)","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 9th International Conference on Data Science and Advanced Analytics (DSAA)","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/A5068186778","display_name":"Chendong Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]},{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chendong Zhao","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd.,Shenzhen,China","Ping An Technology (Shenzhen) Co., Ltd., Shenzhen, China","The Shenzhen International Graduate School, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd.,Shenzhen,China","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4401726822"]},{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd., Shenzhen, China","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4401726822"]},{"raw_affiliation_string":"The Shenzhen International Graduate School, Tsinghua University, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074472751","display_name":"Jianzong Wang","orcid":"https://orcid.org/0000-0002-9237-4231"},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]},{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianzong Wang","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd.,Shenzhen,China","Ping An Technology (Shenzhen) Co., Ltd., Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd.,Shenzhen,China","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4401726822"]},{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd., Shenzhen, China","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069331320","display_name":"Wenqi Wei","orcid":"https://orcid.org/0000-0001-9177-114X"},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]},{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenqi Wei","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd.,Shenzhen,China","Ping An Technology (Shenzhen) Co., Ltd., Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd.,Shenzhen,China","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4401726822"]},{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd., Shenzhen, China","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100940847","display_name":"Xiaoyang Qu","orcid":"https://orcid.org/0009-0009-6311-4332"},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]},{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyang Qu","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd.,Shenzhen,China","Ping An Technology (Shenzhen) Co., Ltd., Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd.,Shenzhen,China","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4401726822"]},{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd., Shenzhen, China","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028229824","display_name":"Haoqian Wang","orcid":"https://orcid.org/0000-0003-2792-8469"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoqian Wang","raw_affiliation_strings":["Tsinghua University,The Shenzhen International Graduate School,China","The Shenzhen International Graduate School, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,The Shenzhen International Graduate School,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"The Shenzhen International Graduate School, Tsinghua University, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016038454","display_name":"Jing Xiao","orcid":"https://orcid.org/0000-0001-9615-4749"},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]},{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Xiao","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd.,Shenzhen,China","Ping An Technology (Shenzhen) Co., Ltd., Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd.,Shenzhen,China","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4401726822"]},{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd., Shenzhen, China","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4401726822"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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":0.76108674,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.9991000294685364,"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":0.7942063808441162},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.7391389608383179},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6374397277832031},{"id":"https://openalex.org/keywords/monotonic-function","display_name":"Monotonic function","score":0.5959973335266113},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.536508321762085},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5102031230926514},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34092116355895996},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.16686755418777466},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08228448033332825},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.0764293372631073}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7942063808441162},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.7391389608383179},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6374397277832031},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.5959973335266113},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.536508321762085},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5102031230926514},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34092116355895996},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.16686755418777466},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08228448033332825},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0764293372631073},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dsaa54385.2022.10032360","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsaa54385.2022.10032360","pdf_url":null,"source":{"id":"https://openalex.org/S4363608340","display_name":"2022 IEEE 9th International Conference on Data Science and Advanced Analytics (DSAA)","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 9th International Conference on Data Science and Advanced Analytics (DSAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W854541894","https://openalex.org/W2077574606","https://openalex.org/W2127141656","https://openalex.org/W2327501763","https://openalex.org/W2526425061","https://openalex.org/W2619122421","https://openalex.org/W2904818793","https://openalex.org/W2912206855","https://openalex.org/W2913718171","https://openalex.org/W2936123380","https://openalex.org/W2950858167","https://openalex.org/W2952992734","https://openalex.org/W2963062480","https://openalex.org/W2963242190","https://openalex.org/W2963400424","https://openalex.org/W2970777192","https://openalex.org/W2972389417","https://openalex.org/W2972439411","https://openalex.org/W2972778435","https://openalex.org/W2973215447","https://openalex.org/W2976556660","https://openalex.org/W2997753998","https://openalex.org/W3007528493","https://openalex.org/W3015671919","https://openalex.org/W3016072087","https://openalex.org/W3097125541","https://openalex.org/W3097777922","https://openalex.org/W3148654612","https://openalex.org/W3160622492","https://openalex.org/W3162016613","https://openalex.org/W3162431424","https://openalex.org/W3196787717","https://openalex.org/W3202022704","https://openalex.org/W4221160948","https://openalex.org/W4221160950","https://openalex.org/W4226277663","https://openalex.org/W4312380264","https://openalex.org/W4312527085","https://openalex.org/W4312813914","https://openalex.org/W4385245566","https://openalex.org/W6623517193","https://openalex.org/W6691766336","https://openalex.org/W6735706088","https://openalex.org/W6738577479","https://openalex.org/W6747158283","https://openalex.org/W6747963193","https://openalex.org/W6751674603","https://openalex.org/W6761628794","https://openalex.org/W6768570733","https://openalex.org/W6803606285"],"related_works":["https://openalex.org/W3107204728","https://openalex.org/W4287591324","https://openalex.org/W4226420367","https://openalex.org/W2980176872","https://openalex.org/W2962876041","https://openalex.org/W3090555870","https://openalex.org/W3108503355","https://openalex.org/W2249953602","https://openalex.org/W2801655600","https://openalex.org/W2912971006"],"abstract_inverted_index":{"The":[0,86,105,119],"Transformer":[1,38,58],"architecture":[2],"model,":[3],"based":[4],"on":[5,131],"self-attention":[6,22,36,97],"and":[7,23,80],"multi-head":[8,24,55,116],"attention,":[9],"has":[10],"achieved":[11],"remarkable":[12],"success":[13],"in":[14,37,57,68],"offline":[15],"end-to-end":[16],"Automatic":[17],"Speech":[18],"Recognition":[19],"(ASR).":[20],"However,":[21],"attention":[25,44,56,79,82,107,117,129],"cannot":[26],"be":[27],"easily":[28],"applied":[29],"for":[30,114],"streaming":[31],"or":[32],"online":[33],"ASR.":[34,85],"For":[35,54],"ASR,":[39,59],"the":[40,101,115,128],"softmax":[41],"normalization":[42],"function-based":[43],"mechanism":[45,88,130],"makes":[46],"it":[47,60],"impossible":[48],"to":[49,64,94,99,110],"highlight":[50],"important":[51],"speech":[52,136],"information.":[53],"is":[61],"not":[62],"easy":[63],"model":[65],"monotonic":[66,81,106],"alignments":[67],"different":[69],"heads.":[70],"To":[71],"overcome":[72],"these":[73],"two":[74],"limits,":[75],"we":[76],"integrate":[77],"sparse":[78,87],"into":[83],"Transformer-based":[84],"introduces":[89],"a":[90],"learned":[91],"sparsity":[92],"scheme":[93],"enable":[95],"each":[96],"structure":[98],"fit":[100],"corresponding":[102],"head":[103],"better.":[104],"deploys":[108],"regularization":[109],"prune":[111],"redundant":[112],"heads":[113],"structure.":[118],"experiments":[120],"show":[121],"that":[122],"our":[123],"method":[124],"can":[125],"effectively":[126],"improve":[127],"widely":[132],"used":[133],"benchmarks":[134],"of":[135],"recognition.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}