{"id":"https://openalex.org/W2944686050","doi":"https://doi.org/10.1109/iscslp.2018.8706645","title":"Distant-talking Speech Recognition Based on Multi-objective Learning using Phase and Magnitude-based Feature","display_name":"Distant-talking Speech Recognition Based on Multi-objective Learning using Phase and Magnitude-based Feature","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2944686050","doi":"https://doi.org/10.1109/iscslp.2018.8706645","mag":"2944686050"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2018.8706645","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706645","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5067766102","display_name":"Dongbo Li","orcid":"https://orcid.org/0000-0001-9593-2043"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dongbo Li","raw_affiliation_strings":["Tianjin Key Laboratory of Cognitive Computing and Application, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101745213","display_name":"Longbiao Wang","orcid":"https://orcid.org/0000-0002-8094-6861"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longbiao Wang","raw_affiliation_strings":["Tianjin Key Laboratory of Cognitive Computing and Application, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017251198","display_name":"Jianwu Dang","orcid":"https://orcid.org/0000-0002-9237-4821"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianwu Dang","raw_affiliation_strings":["Tianjin Key Laboratory of Cognitive Computing and Application, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071074013","display_name":"Meng Ge","orcid":"https://orcid.org/0000-0003-2017-4529"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Ge","raw_affiliation_strings":["Tianjin Key Laboratory of Cognitive Computing and Application, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025700414","display_name":"Haotian Guan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haotian Guan","raw_affiliation_strings":["Intelligent Spoken Language Technology (Tianjin) Co., Ltd., Tianjin, China","Intelligent Spoken Language Technology (Tianjin) Co., Ltd.,, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Intelligent Spoken Language Technology (Tianjin) Co., Ltd., Tianjin, China","institution_ids":[]},{"raw_affiliation_string":"Intelligent Spoken Language Technology (Tianjin) Co., Ltd.,, Tianjin, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5067766102"],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":0.1651,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.50745873,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"394","last_page":"398"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9990000128746033,"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":0.9983999729156494,"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/computer-science","display_name":"Computer science","score":0.7962610721588135},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7712363004684448},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6835125088691711},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5799494981765747},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5599361658096313},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5387580990791321},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5372971892356873},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5256907939910889},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5047670602798462},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.49441099166870117},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.46516066789627075},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46510133147239685},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4365840554237366},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.41376814246177673},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.07716608047485352}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7962610721588135},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7712363004684448},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6835125088691711},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5799494981765747},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5599361658096313},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5387580990791321},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5372971892356873},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5256907939910889},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5047670602798462},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.49441099166870117},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.46516066789627075},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46510133147239685},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4365840554237366},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.41376814246177673},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.07716608047485352},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2018.8706645","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706645","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.47999998927116394}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1519782245","https://openalex.org/W1991344254","https://openalex.org/W2002311796","https://openalex.org/W2032252376","https://openalex.org/W2044893557","https://openalex.org/W2070126272","https://openalex.org/W2072184010","https://openalex.org/W2078528584","https://openalex.org/W2084620644","https://openalex.org/W2109000787","https://openalex.org/W2119000949","https://openalex.org/W2122787031","https://openalex.org/W2145212718","https://openalex.org/W2161153290","https://openalex.org/W2165644552","https://openalex.org/W2198098822","https://openalex.org/W2397226255","https://openalex.org/W2401447047","https://openalex.org/W2402466562","https://openalex.org/W2403766732","https://openalex.org/W2406845569","https://openalex.org/W2513927927","https://openalex.org/W2606361731","https://openalex.org/W2746321128","https://openalex.org/W2748545504","https://openalex.org/W2789949544","https://openalex.org/W2950258612","https://openalex.org/W2963590520","https://openalex.org/W6684671274","https://openalex.org/W6712317276","https://openalex.org/W6713058952","https://openalex.org/W6713298849","https://openalex.org/W6713808294","https://openalex.org/W6713813118","https://openalex.org/W7061913096"],"related_works":["https://openalex.org/W1482212662","https://openalex.org/W2100012411","https://openalex.org/W3162157266","https://openalex.org/W2162084437","https://openalex.org/W1997579527","https://openalex.org/W2102353451","https://openalex.org/W3044927199","https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097"],"abstract_inverted_index":{"Deep":[0],"neural":[1,67,133],"network":[2,68],"for":[3,27,42,51],"speech":[4,29,44,55,72,116,124],"enhancement":[5,73,76],"is":[6,40,49,152],"an":[7],"increasingly":[8],"interesting":[9],"topic.":[10],"In":[11,31,98],"this":[12,59,61,99],"paper,":[13,100],"we":[14,101],"propose":[15],"a":[16,65],"multi-objective":[17,66],"learning":[18],"method":[19,69,113,145],"to":[20,70,110,140],"using":[21,64,137],"the":[22,103,143,147],"amplitude":[23],"and":[24,74,87,146],"phase":[25,38,47,79],"information":[26,39,48],"reverberant":[28],"recognition.":[30,56,117],"previous":[32],"studies,":[33],"some":[34],"researches":[35],"found":[36],"that":[37],"important":[41],"human":[43],"recognition,":[45],"but":[46],"ignored":[50],"almost":[52],"front-end":[53],"of":[54,106,123,130,142],"To":[57],"address":[58],"problem,":[60],"paper":[62],"proposes":[63],"optimize":[71],"feature":[75],"simultaneously.":[77],"For":[78],"information,":[80],"Modied":[81],"Group":[82],"Delay":[83],"Cepstral":[84],"Coefcients":[85],"(MGDCC)":[86],"Phase":[88],"Domain":[89],"Source-Filter":[90],"separation":[91],"based":[92,135],"Vocal":[93],"Tract":[94],"(PBSFVT)":[95],"are":[96],"used.":[97],"use":[102],"data":[104],"set":[105],"Reverb":[107],"Challenge":[108],"2014":[109],"evaluate":[111],"proposed":[112,144],"on":[114],"distant-talking":[115],"The":[118],"Word":[119],"Error":[120],"Rate":[121],"(WER)":[122],"recognition":[125],"was":[126],"reduced":[127],"from":[128],"26.57%":[129],"traditional":[131],"deep":[132],"work":[134],"dereverberation":[136],"magnitude":[138],"feature,":[139],"23.34%":[141],"relative":[148],"error":[149],"reduction":[150],"rate":[151],"12.15%.":[153]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}