{"id":"https://openalex.org/W3011946518","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023325","title":"Robust Speech Recognition based on Multi-Objective Learning with GRU Network","display_name":"Robust Speech Recognition based on Multi-Objective Learning with GRU Network","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3011946518","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023325","mag":"3011946518"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc47483.2019.9023325","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023325","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":"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/A5100661062","display_name":"Ming Liu","orcid":"https://orcid.org/0000-0002-1861-1315"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ming Liu","raw_affiliation_strings":["Xiao Inc, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiao Inc, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362608","display_name":"Yujun Wang","orcid":"https://orcid.org/0000-0003-2335-0946"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yujun Wang","raw_affiliation_strings":["Xiao Inc, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiao Inc, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046831667","display_name":"Zhaoyu Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaoyu Yan","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100378497","display_name":"Jing Wang","orcid":"https://orcid.org/0000-0002-3653-9951"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Wang","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100642396","display_name":"Xiang Xie","orcid":"https://orcid.org/0000-0002-6895-3145"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Xie","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100661062"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.19896895,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"181","last_page":"185"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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/T11309","display_name":"Music and Audio Processing","score":0.9980000257492065,"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":0.8090119361877441},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7704821228981018},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5736781358718872},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5707370042800903},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5332801938056946},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5310882329940796},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5253357887268066},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5204501152038574},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.517113208770752},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4735240936279297},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4476274847984314},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41504496335983276},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.41403326392173767},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11499127745628357}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8090119361877441},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7704821228981018},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5736781358718872},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5707370042800903},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5332801938056946},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5310882329940796},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5253357887268066},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5204501152038574},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.517113208770752},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4735240936279297},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4476274847984314},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41504496335983276},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.41403326392173767},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11499127745628357},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc47483.2019.9023325","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023325","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1495679096","https://openalex.org/W1614862348","https://openalex.org/W2013608223","https://openalex.org/W2044893557","https://openalex.org/W2064675550","https://openalex.org/W2077651652","https://openalex.org/W2088137865","https://openalex.org/W2094035326","https://openalex.org/W2103075368","https://openalex.org/W2121029939","https://openalex.org/W2141493634","https://openalex.org/W2143612262","https://openalex.org/W2147768505","https://openalex.org/W2160815625","https://openalex.org/W2397226255","https://openalex.org/W2408592723","https://openalex.org/W2516310076","https://openalex.org/W2696967604","https://openalex.org/W2950258612","https://openalex.org/W2963341071","https://openalex.org/W3209042722","https://openalex.org/W4245919820","https://openalex.org/W6713796627"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W4385672897","https://openalex.org/W2373675101","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W2074132948","https://openalex.org/W4317383455","https://openalex.org/W2548511587"],"abstract_inverted_index":{"This":[0,123],"paper":[1],"proposes":[2],"a":[3],"new":[4,157],"scheme":[5,159,177],"to":[6,55,69,102,114,139,146,189],"execute":[7],"the":[8,26,38,42,49,72,80,111,116,121,136,140,143,149,156,165,171,180,186,190],"task":[9,45],"of":[10,173,185],"speech":[11],"enhancement":[12],"(SE)":[13],"for":[14,41],"recognition":[15],"based":[16],"on":[17,128],"multi-objective":[18,158],"learning":[19,76,95,168],"method":[20,169],"which":[21],"uses":[22],"three":[23],"objectives":[24],"in":[25],"gated":[27],"recurrent":[28],"unit":[29],"(GRU)":[30],"network":[31,117,145,194],"training":[32],"procedure.":[33],"The":[34,62,85,105,151],"first":[35],"objective":[36],"is":[37,65,88],"main":[39,73],"target":[40,68,92],"expected":[43],"SE":[44],"by":[46,75,94,119],"directly":[47],"mapping":[48,99,131,163],"noisy":[50,100],"log-power":[51],"spectrum":[52],"(LPS)":[53],"features":[54],"clean":[56,103],"Mel-frequency":[57],"cepstral":[58],"coefficients":[59],"(MFCC)":[60],"features.":[61],"second":[63],"one":[64,74,87],"an":[66,90],"auxiliary":[67,91,107],"help":[70,110],"improving":[71],"additional":[77],"information":[78,97,133],"from":[79,98,135],"backend":[81],"acoustic":[82,137],"model":[83,138],"(AM).":[84],"third":[86],"also":[89],"achieved":[93],"some":[96],"LPS":[101],"LPS.":[104],"two":[106],"structures":[108],"could":[109],"original":[112],"structure":[113],"optimize":[115],"parameters":[118],"correcting":[120],"errors.":[122],"approach":[124],"imposes":[125],"more":[126],"constraints":[127],"direct":[129],"feature":[130,162],"and":[132,164],"passing":[134],"network,":[141],"enabling":[142],"enhanced":[144],"better":[147],"serve":[148],"AM.":[150],"experimental":[152],"results":[153],"show":[154],"that":[155],"with":[160],"joint":[161],"posterior":[166],"probability":[167],"improves":[170],"performance":[172],"SE.":[174],"And":[175],"this":[176],"significantly":[178],"lowers":[179],"Character":[181],"Error":[182],"Rate":[183],"(CER)":[184],"AM":[187],"compared":[188],"baseline":[191],"deep":[192],"neural":[193],"(DNN)":[195],"network.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}