{"id":"https://openalex.org/W4392909899","doi":"https://doi.org/10.1109/icassp48485.2024.10446106","title":"SeACo-Paraformer: A Non-Autoregressive ASR System with Flexible and Effective Hotword Customization Ability","display_name":"SeACo-Paraformer: A Non-Autoregressive ASR System with Flexible and Effective Hotword Customization Ability","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909899","doi":"https://doi.org/10.1109/icassp48485.2024.10446106"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446106","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446106","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5062644421","display_name":"Xian Shi","orcid":"https://orcid.org/0000-0002-4120-7361"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xian Shi","raw_affiliation_strings":["Alibaba Group,Speech Lab of DAMO Academy,China","Speech Lab of DAMO Academy, Alibaba Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab of DAMO Academy,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Speech Lab of DAMO Academy, Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101650603","display_name":"Yexin Yang","orcid":"https://orcid.org/0000-0001-7651-2940"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yexin Yang","raw_affiliation_strings":["Alibaba Group,Speech Lab of DAMO Academy,China","Speech Lab of DAMO Academy, Alibaba Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab of DAMO Academy,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Speech Lab of DAMO Academy, Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111046223","display_name":"Zerui Li","orcid":"https://orcid.org/0009-0004-0812-8479"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zerui Li","raw_affiliation_strings":["Alibaba Group,Speech Lab of DAMO Academy,China","Speech Lab of DAMO Academy, Alibaba Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab of DAMO Academy,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Speech Lab of DAMO Academy, Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102756307","display_name":"Yanni Chen","orcid":"https://orcid.org/0000-0002-0436-6937"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanni Chen","raw_affiliation_strings":["Alibaba Group,Speech Lab of DAMO Academy,China","Speech Lab of DAMO Academy, Alibaba Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab of DAMO Academy,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Speech Lab of DAMO Academy, Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109593343","display_name":"Zhifu Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhifu Gao","raw_affiliation_strings":["Alibaba Group,Speech Lab of DAMO Academy,China","Speech Lab of DAMO Academy, Alibaba Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab of DAMO Academy,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Speech Lab of DAMO Academy, Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101777591","display_name":"Shiliang Zhang","orcid":"https://orcid.org/0000-0002-9524-1602"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiliang Zhang","raw_affiliation_strings":["Alibaba Group,Speech Lab of DAMO Academy,China","Speech Lab of DAMO Academy, Alibaba Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab of DAMO Academy,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Speech Lab of DAMO Academy, Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I45928872"],"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":"10346","last_page":"10350"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.868399977684021,"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":0.868399977684021,"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/personalization","display_name":"Personalization","score":0.7544137239456177},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.7160263061523438},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7068682909011841},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1788247525691986},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.09556296467781067},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07490170001983643}],"concepts":[{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.7544137239456177},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.7160263061523438},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7068682909011841},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1788247525691986},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.09556296467781067},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07490170001983643}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446106","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446106","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1604697534","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2327501763","https://openalex.org/W2395440424","https://openalex.org/W2808640845","https://openalex.org/W2810578980","https://openalex.org/W2886319145","https://openalex.org/W2963242190","https://openalex.org/W2963414781","https://openalex.org/W2972741966","https://openalex.org/W2972818416","https://openalex.org/W3007328579","https://openalex.org/W3015974384","https://openalex.org/W3016167541","https://openalex.org/W3095687747","https://openalex.org/W3097580812","https://openalex.org/W3097794466","https://openalex.org/W3160413945","https://openalex.org/W4224918838","https://openalex.org/W4225289150","https://openalex.org/W4225644313","https://openalex.org/W4283067311","https://openalex.org/W4385245566","https://openalex.org/W4385822246","https://openalex.org/W4385822407","https://openalex.org/W6752630080","https://openalex.org/W6752790335","https://openalex.org/W6784721964"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2109940557","https://openalex.org/W2466832359","https://openalex.org/W4391210591","https://openalex.org/W2171218219","https://openalex.org/W1582019636","https://openalex.org/W1972271943","https://openalex.org/W2150410159","https://openalex.org/W2390279801"],"abstract_inverted_index":{"Hotword":[0],"customization":[1,83,98],"is":[2,14],"one":[3],"of":[4,15,20,26,89,100,109],"the":[5,60,87],"concerned":[6],"issues":[7],"remained":[8],"in":[9,119],"ASR":[10,21,46,76],"field":[11],"-":[12],"it":[13],"value":[16],"to":[17,23,32,127],"enable":[18],"users":[19],"systems":[22],"customize":[24],"names":[25],"entities,":[27],"persons":[28],"and":[29,59,80,96,141],"other":[30],"phrases":[31],"obtain":[33],"better":[34],"experience.":[35],"The":[36,135],"past":[37],"few":[38],"years":[39],"have":[40],"seen":[41],"effective":[42,81],"modeling":[43],"strategies":[44],"for":[45,54,132],"contextualization":[47],"developed,":[48],"but":[49],"they":[50],"still":[51],"exhibit":[52],"space":[53],"improvement":[55],"about":[56],"training":[57],"stability":[58],"invisible":[61],"activation":[62],"process.":[63],"In":[64],"this":[65],"paper":[66],"we":[67,122],"propose":[68],"Semantic-Augmented":[69],"Contextual-Paraformer":[70],"(SeACo-Paraformer)":[71],"a":[72],"novel":[73],"NAR":[74,93],"based":[75],"system":[77],"with":[78,106],"flexible":[79],"hotword":[82,143],"ability.":[84],"It":[85],"possesses":[86],"advantages":[88],"AED-based":[90],"model\u2019s":[91,94],"accuracy,":[92],"efficiency,":[95],"explicit":[97],"capacity":[99],"superior":[101],"performance.":[102],"Through":[103],"extensive":[104],"experiments":[105],"50,000":[107],"hours":[108],"industrial":[110,136],"big":[111],"data,":[112],"our":[113],"proposed":[114],"model":[115],"outperforms":[116],"strong":[117],"baselines":[118],"customization.":[120],"Besides,":[121],"explore":[123],"an":[124],"efficient":[125],"way":[126],"filter":[128],"large-scale":[129],"incoming":[130],"hotwords":[131],"further":[133],"improvement.":[134],"models":[137],"compared,":[138],"source":[139],"codes":[140],"two":[142],"test":[144],"sets":[145],"are":[146],"all":[147],"open":[148],"source.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}