{"id":"https://openalex.org/W3012065388","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023204","title":"Dynamic-attention based Encoder-decoder model for Speaker Extraction with Anchor speech","display_name":"Dynamic-attention based Encoder-decoder model for Speaker Extraction with Anchor speech","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3012065388","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023204","mag":"3012065388"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc47483.2019.9023204","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023204","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5100348721","display_name":"Hao Li","orcid":"https://orcid.org/0009-0005-4319-9026"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Li","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693230","display_name":"Xueliang Zhang","orcid":"https://orcid.org/0000-0002-0406-1105"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueliang Zhang","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076174513","display_name":"Guanglai Gao","orcid":"https://orcid.org/0009-0005-5513-1192"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanglai Gao","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, China","institution_ids":["https://openalex.org/I2722730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2722730"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9986000061035156,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9866999983787537,"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":0.8145028948783875},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7746399641036987},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.624752402305603},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6194685697555542},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5289456844329834},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4827243983745575},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.4787030518054962},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.47786396741867065},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.46206435561180115},{"id":"https://openalex.org/keywords/interference","display_name":"Interference (communication)","score":0.4194380044937134},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4118981957435608},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4043535590171814},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3444012403488159},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.21666085720062256},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.17107629776000977},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.08017975091934204},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06723302602767944}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8145028948783875},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7746399641036987},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.624752402305603},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6194685697555542},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5289456844329834},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4827243983745575},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.4787030518054962},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.47786396741867065},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.46206435561180115},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.4194380044937134},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4118981957435608},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4043535590171814},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3444012403488159},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.21666085720062256},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.17107629776000977},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.08017975091934204},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06723302602767944},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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:10.1109/apsipaasc47483.2019.9023204","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023204","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":24,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1522301498","https://openalex.org/W1523691755","https://openalex.org/W1552314771","https://openalex.org/W1902237438","https://openalex.org/W2095705004","https://openalex.org/W2127851351","https://openalex.org/W2133564696","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2558649592","https://openalex.org/W2568308529","https://openalex.org/W2587603783","https://openalex.org/W2749510669","https://openalex.org/W2749659773","https://openalex.org/W2891833136","https://openalex.org/W2962866211","https://openalex.org/W2963247703","https://openalex.org/W4243599615","https://openalex.org/W6623517193","https://openalex.org/W6631190155","https://openalex.org/W6631302301","https://openalex.org/W6674330103","https://openalex.org/W6679434410"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1999004162","https://openalex.org/W4200596008"],"abstract_inverted_index":{"Speech":[0],"plays":[1],"an":[2,12],"important":[3],"role":[4],"in":[5],"human-computer":[6],"interaction.":[7],"For":[8],"many":[9],"real":[10],"applications,":[11],"annoying":[13],"problem":[14,47],"is":[15,18,30,39,63,89,120],"that":[16,136],"speech":[17,26,61,84,108],"often":[19],"degraded":[20],"by":[21],"interfering":[22,53],"noise.":[23],"Extracting":[24],"target":[25,50,68,96,107],"from":[27,52,109],"background":[28],"interference":[29,38],"a":[31,56,73,86,113,124],"meaningful":[32],"and":[33],"challenging":[34],"task,":[35],"especially":[36],"when":[37],"also":[40],"human":[41],"voice.":[42],"This":[43],"work":[44],"addresses":[45],"the":[46,67,79,82,93,101,106,131,140],"of":[48,59,95,130,142],"extracting":[49],"speaker":[51,54,69,102,115,143],"with":[55],"short":[57],"piece":[58],"anchor":[60,83],"which":[62,88],"used":[64,90],"to":[65,85,91,104,122],"obtain":[66],"identify.":[70],"We":[71],"propose":[72],"encoder-decoder":[74],"neural":[75],"network":[76],"architecture.":[77],"Specifically,":[78],"encoder":[80],"transforms":[81],"embedding":[87,126],"represent":[92],"identity":[94,103],"speaker.":[97],"The":[98,117],"decoder":[99],"utilizes":[100],"extract":[105],"mixture.":[110,132],"To":[111],"make":[112],"acoustic-related":[114],"identity,":[116],"dynamic-attention":[118],"mechanism":[119],"utilized":[121],"build":[123],"time-varying":[125],"for":[127],"each":[128],"frame":[129],"Systematic":[133],"evaluation":[134],"indicates":[135],"our":[137],"approach":[138],"improves":[139],"quality":[141],"extraction.":[144]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}