{"id":"https://openalex.org/W3016230414","doi":"https://doi.org/10.1109/icassp40776.2020.9053629","title":"Deep Speech Extraction with Time-Varying Spatial Filtering Guided By Desired Direction Attractor","display_name":"Deep Speech Extraction with Time-Varying Spatial Filtering Guided By Desired Direction Attractor","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016230414","doi":"https://doi.org/10.1109/icassp40776.2020.9053629","mag":"3016230414"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5070736822","display_name":"Yu Nakagome","orcid":"https://orcid.org/0000-0002-5837-8212"},"institutions":[{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yu Nakagome","raw_affiliation_strings":["LINE Corporation, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"LINE Corporation, Tokyo, Japan","institution_ids":["https://openalex.org/I4210096607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021883714","display_name":"Masahito Togami","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masahito Togami","raw_affiliation_strings":["LINE Corporation, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"LINE Corporation, Tokyo, Japan","institution_ids":["https://openalex.org/I4210096607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087632404","display_name":"Tetsuji Ogawa","orcid":"https://orcid.org/0000-0002-7316-2073"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuji Ogawa","raw_affiliation_strings":["Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101188700","display_name":"Tetsunori Kobayashi","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsunori Kobayashi","raw_affiliation_strings":["Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5070736822"],"corresponding_institution_ids":["https://openalex.org/I4210096607"],"apc_list":null,"apc_paid":null,"fwci":0.3031,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.51639236,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"671","last_page":"675"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9986000061035156,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7455308437347412},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6369571089744568},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5308533310890198},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4886992275714874},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4446222484111786},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.44198817014694214},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4276348054409027},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.391195148229599},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2288602888584137},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.0862061083316803}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7455308437347412},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6369571089744568},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5308533310890198},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4886992275714874},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4446222484111786},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.44198817014694214},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4276348054409027},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.391195148229599},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2288602888584137},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0862061083316803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1543386260","https://openalex.org/W1845880232","https://openalex.org/W1983108229","https://openalex.org/W1996304098","https://openalex.org/W2031583051","https://openalex.org/W2046869671","https://openalex.org/W2096230913","https://openalex.org/W2099741732","https://openalex.org/W2127851351","https://openalex.org/W2143027228","https://openalex.org/W2221409856","https://openalex.org/W2288669569","https://openalex.org/W2412956798","https://openalex.org/W2460742184","https://openalex.org/W2558649592","https://openalex.org/W2578331995","https://openalex.org/W2735663686","https://openalex.org/W2749510669","https://openalex.org/W2792498316","https://openalex.org/W2891833136","https://openalex.org/W2937235446","https://openalex.org/W2964121744","https://openalex.org/W2972802573","https://openalex.org/W3124972797","https://openalex.org/W3127686677","https://openalex.org/W4245919820","https://openalex.org/W6631190155","https://openalex.org/W6632571750","https://openalex.org/W6917638038"],"related_works":["https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2120771489","https://openalex.org/W2275432853","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W2089240210","https://openalex.org/W2131486661","https://openalex.org/W2981428355"],"abstract_inverted_index":{"In":[0],"this":[1],"investigation,":[2],"a":[3,16,31,40,44,51],"deep":[4],"neural":[5],"network":[6],"(DNN)":[7],"based":[8,29,102],"speech":[9,17,41,53,62,87,115,132,139,144],"extraction":[10,63,145],"method":[11,26,127],"is":[12,99],"proposed":[13,25,126],"to":[14,84],"enhance":[15],"signal":[18,92],"propagating":[19],"from":[20],"the":[21,36,72,86,90,104,113,125,130],"desired":[22],"direction.":[23],"The":[24,120],"integrates":[27],"knowledge":[28],"on":[30,103],"sound":[32,105],"propagation":[33,106],"model":[34],"and":[35,117,142],"time-varying":[37,56],"characteristics":[38],"of":[39,74,89,112],"source,":[42],"into":[43],"DNN-based":[45,138],"separation":[46,141],"framework.":[47],"This":[48],"approach":[49],"outputs":[50],"separated":[52],"source":[54,116,133,140],"using":[55,146],"spatial":[57,68,148],"filtering,":[58],"which":[59,108],"achieves":[60],"superior":[61],"performance":[64],"compared":[65],"with":[66],"time-invariant":[67,147],"filtering.":[69,149],"Given":[70],"that":[71,124],"gradient":[73],"all":[75],"modules":[76],"can":[77,81,128],"be":[78,82],"calculated,":[79],"back-propagation":[80],"performed":[83],"maximize":[85],"quality":[88],"output":[91],"in":[93],"an":[94],"end-to-end":[95],"manner.":[96],"Guided":[97],"information":[98],"also":[100],"modeled":[101],"model,":[107],"facilitates":[109],"disentangled":[110],"representations":[111],"target":[114,131],"noise":[118],"signals.":[119],"experimental":[121],"results":[122],"demonstrate":[123],"extract":[129],"more":[134],"accurately":[135],"than":[136],"conventional":[137,143]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}