{"id":"https://openalex.org/W2920796740","doi":"https://doi.org/10.23919/apsipa.2018.8659609","title":"Online Speaker Adaptation for LVCSR Based on Attention Mechanism","display_name":"Online Speaker Adaptation for LVCSR Based on Attention Mechanism","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2920796740","doi":"https://doi.org/10.23919/apsipa.2018.8659609","mag":"2920796740"},"language":"en","primary_location":{"id":"doi:10.23919/apsipa.2018.8659609","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659609","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5101924451","display_name":"Jia Pan","orcid":"https://orcid.org/0000-0002-7073-1744"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jia Pan","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060287819","display_name":"Diyuan Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Diyuan Liu","raw_affiliation_strings":["iFlytek Research, iFlytek Co., Ltd., Hefei, Anhui, P. R. China"],"affiliations":[{"raw_affiliation_string":"iFlytek Research, iFlytek Co., Ltd., Hefei, Anhui, P. R. China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011133553","display_name":"Genshun Wan","orcid":"https://orcid.org/0000-0002-5813-9430"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Genshun Wan","raw_affiliation_strings":["iFlytek Research, iFlytek Co., Ltd., Hefei, Anhui, P. R. China"],"affiliations":[{"raw_affiliation_string":"iFlytek Research, iFlytek Co., Ltd., Hefei, Anhui, P. R. China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066595711","display_name":"Jun Du","orcid":"https://orcid.org/0000-0002-2387-0389"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Du","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039181878","display_name":"Qingfeng Liu","orcid":"https://orcid.org/0000-0001-5437-4946"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qingfeng Liu","raw_affiliation_strings":["iFlytek Research, iFlytek Co., Ltd., Hefei, Anhui, P. R. China"],"affiliations":[{"raw_affiliation_string":"iFlytek Research, iFlytek Co., Ltd., Hefei, Anhui, P. R. China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065761465","display_name":"Zhongfu Ye","orcid":"https://orcid.org/0000-0002-3207-2258"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongfu Ye","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101924451"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":1.6288,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.88099499,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"183","last_page":"186"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.996999979019165,"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":0.9908000230789185,"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":0.8719202280044556},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7880370020866394},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6436939835548401},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6046519875526428},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5710023641586304},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5535663366317749},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5191963911056519},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.509297251701355},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4873269498348236},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48340049386024475},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4374026656150818},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.43733835220336914},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42270150780677795},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3357003927230835}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8719202280044556},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7880370020866394},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6436939835548401},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6046519875526428},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5710023641586304},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5535663366317749},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5191963911056519},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.509297251701355},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4873269498348236},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48340049386024475},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4374026656150818},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.43733835220336914},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42270150780677795},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3357003927230835},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/apsipa.2018.8659609","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659609","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6399999856948853,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1513820424","https://openalex.org/W1770758908","https://openalex.org/W1989549063","https://openalex.org/W1993409002","https://openalex.org/W2079623482","https://openalex.org/W2090320273","https://openalex.org/W2094147890","https://openalex.org/W2112021726","https://openalex.org/W2133564696","https://openalex.org/W2147768505","https://openalex.org/W2150769028","https://openalex.org/W2198724430","https://openalex.org/W2293634267","https://openalex.org/W2296483664","https://openalex.org/W2400607496","https://openalex.org/W2407793339","https://openalex.org/W2641129314","https://openalex.org/W2891286407","https://openalex.org/W2964308564","https://openalex.org/W6623517193","https://openalex.org/W6674052071","https://openalex.org/W6679434410","https://openalex.org/W6696934422","https://openalex.org/W6697003656","https://openalex.org/W6713823255"],"related_works":["https://openalex.org/W1997182898","https://openalex.org/W2206035908","https://openalex.org/W1493012537","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W1999004162","https://openalex.org/W4280634406"],"abstract_inverted_index":{"Speaker":[0],"adaptation":[1,23,128],"is":[2,58,132,146],"one":[3],"of":[4,41,100,136,151],"the":[5,39,42,62,68,73,84,90,98,105,110,137,152],"most":[6,63],"popular":[7,138],"and":[8,145],"important":[9],"topics":[10],"for":[11,25,96],"speech":[12,33,70,101],"recognition.":[13,102],"In":[14,36],"this":[15,37],"paper,":[16],"we":[17],"propose":[18,77],"a":[19,50,78,114],"novel":[20],"online":[21,155],"speaker":[22,65,94,123,142,156],"technique":[24],"deep":[26],"neural":[27],"networks":[28],"based":[29,140,154],"large":[30],"vocabulary":[31],"automatic":[32],"recognition":[34],"(LVCSR).":[35],"approach,":[38],"i-vectors":[40,66],"speakers":[43],"in":[44],"training":[45],"set":[46],"are":[47],"extracted":[48],"as":[49],"static":[51],"memory.":[52,74],"For":[53],"each":[54],"frame,":[55],"attention":[56,80,91],"mechanism":[57,81,92],"used":[59],"to":[60,67,82,134],"select":[61],"relevant":[64],"current":[69],"segment":[71],"from":[72],"We":[75],"also":[76],"new":[79],"improve":[83],"performance.":[85],"The":[86,130],"vectors":[87],"obtained":[88],"by":[89],"provide":[93],"information":[95],"improving":[97],"accuracy":[99],"Experiments":[103],"on":[104],"Switchboard":[106],"task":[107],"show":[108],"that":[109,135,150],"proposed":[111],"approach":[112],"achieves":[113],"relative":[115],"8.3%":[116],"word":[117],"error":[118],"rate":[119],"(WER)":[120],"reduction":[121],"over":[122],"independent":[124],"model":[125],"without":[126],"any":[127],"data.":[129],"result":[131],"comparable":[133],"i-vector":[139,153],"offline":[141],"adaption":[143,157],"method":[144],"much":[147],"better":[148],"than":[149],"method.":[158]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}