{"id":"https://openalex.org/W3015424358","doi":"https://doi.org/10.1109/icassp40776.2020.9054597","title":"Real-Time Speech Enhancement Using Equilibriated RNN","display_name":"Real-Time Speech Enhancement Using Equilibriated RNN","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015424358","doi":"https://doi.org/10.1109/icassp40776.2020.9054597","mag":"3015424358"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054597","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054597","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":"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/A5103978078","display_name":"Daiki Takeuchi","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":"Daiki Takeuchi","raw_affiliation_strings":["Department of Intermedia Art and Science, Waseda University, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Intermedia Art and Science, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034837951","display_name":"Kohei Yatabe","orcid":"https://orcid.org/0000-0002-1345-0663"},"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":"Kohei Yatabe","raw_affiliation_strings":["Department of Intermedia Art and Science, Waseda University, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Intermedia Art and Science, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101503856","display_name":"Yuma Koizumi","orcid":"https://orcid.org/0000-0003-3645-6213"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuma Koizumi","raw_affiliation_strings":["NTT Media Intelligence Laboratories, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028428935","display_name":"Yasuhiro Oikawa","orcid":"https://orcid.org/0000-0002-9078-1714"},"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":"Yasuhiro Oikawa","raw_affiliation_strings":["Department of Intermedia Art and Science, Waseda University, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Intermedia Art and Science, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054467679","display_name":"Noboru Harada","orcid":"https://orcid.org/0000-0002-1759-4533"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Noboru Harada","raw_affiliation_strings":["NTT Media Intelligence Laboratories, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.4366,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.95899291,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"851","last_page":"855"},"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":0.9980000257492065,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.8646542429924011},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8212239742279053},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5953760743141174},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5800946950912476},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5704554319381714},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5096430778503418},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5024337768554688},{"id":"https://openalex.org/keywords/long-short-term-memory","display_name":"Long short term memory","score":0.4125784635543823},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35484930872917175}],"concepts":[{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.8646542429924011},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8212239742279053},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5953760743141174},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5800946950912476},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5704554319381714},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5096430778503418},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5024337768554688},{"id":"https://openalex.org/C133488467","wikidata":"https://www.wikidata.org/wiki/Q6673524","display_name":"Long short term memory","level":4,"score":0.4125784635543823},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35484930872917175},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054597","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054597","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":40,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1522301498","https://openalex.org/W1983108229","https://openalex.org/W2064675550","https://openalex.org/W2094721231","https://openalex.org/W2107878631","https://openalex.org/W2144404214","https://openalex.org/W2175402905","https://openalex.org/W2221409856","https://openalex.org/W2603567530","https://openalex.org/W2771725120","https://openalex.org/W2786625961","https://openalex.org/W2889442120","https://openalex.org/W2889597349","https://openalex.org/W2894785362","https://openalex.org/W2899693363","https://openalex.org/W2937484199","https://openalex.org/W2942514267","https://openalex.org/W2943895317","https://openalex.org/W2945191446","https://openalex.org/W2949558265","https://openalex.org/W2950448225","https://openalex.org/W2951605425","https://openalex.org/W2962843322","https://openalex.org/W2962866211","https://openalex.org/W2962923973","https://openalex.org/W2963042606","https://openalex.org/W2963631056","https://openalex.org/W2964121744","https://openalex.org/W2964307104","https://openalex.org/W2969672740","https://openalex.org/W3015219411","https://openalex.org/W3016050488","https://openalex.org/W4298580827","https://openalex.org/W6631190155","https://openalex.org/W6685537299","https://openalex.org/W6729305679","https://openalex.org/W6748409065","https://openalex.org/W6762114000","https://openalex.org/W6766745015"],"related_works":["https://openalex.org/W4385280324","https://openalex.org/W2912153778","https://openalex.org/W2578422401","https://openalex.org/W4387163678","https://openalex.org/W4288108708","https://openalex.org/W2770665941","https://openalex.org/W3096184950","https://openalex.org/W2973430807","https://openalex.org/W2984436043","https://openalex.org/W4390245176"],"abstract_inverted_index":{"We":[0],"propose":[1,122],"a":[2,7,23,29,39,111],"speech":[3,30,104],"enhancement":[4],"method":[5,173],"using":[6],"causal":[8],"deep":[9],"neural":[10,41,128],"network":[11,42,113,129],"(DNN)":[12],"for":[13,21,36,131],"real-time":[14,103],"applications.":[15],"DNN":[16,34],"has":[17],"been":[18],"widely":[19],"used":[20,64],"estimating":[22],"time-frequency":[24],"(T-F)":[25],"mask":[26],"which":[27,71,97,148],"enhances":[28],"signal.":[31],"One":[32],"popular":[33],"structure":[35,145],"that":[37],"is":[38,62,86,107,146],"recurrent":[40,127],"(RNN)":[43],"owing":[44],"to":[45,65,109,123,158,164],"its":[46],"capability":[47],"of":[48,75,82,84,91,95,141],"effectively":[49],"modelling":[50],"time-sequential":[51],"data":[52],"like":[53],"speech.":[54],"In":[55,118],"particular,":[56],"the":[57,67,73,80,89,93,116,125,133,139,151,154,165,171,175],"long":[58],"short-term":[59],"memory":[60],"(LSTM)":[61],"often":[63],"alleviate":[66],"vanishing/exploding":[68,134],"gradient":[69,135],"problem":[70,136],"makes":[72],"training":[74],"an":[76],"RNN":[77],"difficult.":[78],"However,":[79],"number":[81,140],"parameters":[83],"LSTM":[85,169],"increased":[87],"as":[88],"price":[90],"mitigating":[92],"difficulty":[94],"training,":[96],"requires":[98,149],"more":[99],"computational":[100],"resources.":[101],"For":[102],"enhancement,":[105],"it":[106,160],"preferable":[108],"use":[110,124],"smaller":[112],"without":[114,137],"losing":[115],"performance.":[117],"this":[119],"paper,":[120],"we":[121],"equilibriated":[126],"(ERNN)":[130],"avoiding":[132],"increasing":[138],"parameters.":[142,181],"The":[143],"proposed":[144,172],"causal,":[147],"only":[150],"information":[152],"from":[153],"past,":[155],"in":[156,161],"order":[157],"apply":[159],"real-time.":[162],"Compared":[163],"uni-":[166],"and":[167],"bi-directional":[168],"networks,":[170],"achieved":[174],"similar":[176],"performance":[177],"with":[178],"much":[179],"fewer":[180]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}