{"id":"https://openalex.org/W2771500048","doi":"https://doi.org/10.1109/mlsp.2017.8168191","title":"Semi-Blind speech enhancement basedon recurrent neural network for source separation and dereverberation","display_name":"Semi-Blind speech enhancement basedon recurrent neural network for source separation and dereverberation","publication_year":2017,"publication_date":"2017-09-01","ids":{"openalex":"https://openalex.org/W2771500048","doi":"https://doi.org/10.1109/mlsp.2017.8168191","mag":"2771500048"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp.2017.8168191","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp.2017.8168191","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP)","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/A5073724206","display_name":"Masaya Wake","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masaya Wake","raw_affiliation_strings":["Sakyo-ku, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sakyo-ku, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007353694","display_name":"Yoshiaki Bando","orcid":"https://orcid.org/0000-0002-3934-0745"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshiaki Bando","raw_affiliation_strings":["Sakyo-ku, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sakyo-ku, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102851028","display_name":"Masato Mimura","orcid":"https://orcid.org/0000-0002-2403-0680"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masato Mimura","raw_affiliation_strings":["Sakyo-ku, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sakyo-ku, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003325000","display_name":"Katsutoshi Itoyama","orcid":"https://orcid.org/0000-0002-7098-3896"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Katsutoshi Itoyama","raw_affiliation_strings":["Sakyo-ku, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sakyo-ku, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067956319","display_name":"Kazuyoshi Yoshii","orcid":"https://orcid.org/0000-0001-8387-8609"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuyoshi Yoshii","raw_affiliation_strings":["Sakyo-ku, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sakyo-ku, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":["Sakyo-ku, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sakyo-ku, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I22299242"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"87","issue":null,"first_page":"1","last_page":"6"},"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/T11447","display_name":"Blind Source Separation Techniques","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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9904000163078308,"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/computer-science","display_name":"Computer science","score":0.7537800669670105},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7350603342056274},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7242954969406128},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6245956420898438},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.5767701268196106},{"id":"https://openalex.org/keywords/independent-component-analysis","display_name":"Independent component analysis","score":0.5336716175079346},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5158218741416931},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.49572765827178955},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.43234774470329285},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4286873936653137},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4185110032558441},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4076292812824249},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3407859206199646},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.13604581356048584},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.08080348372459412},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.07673931121826172},{"id":"https://openalex.org/keywords/amplifier","display_name":"Amplifier","score":0.0730302631855011}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7537800669670105},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7350603342056274},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7242954969406128},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6245956420898438},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.5767701268196106},{"id":"https://openalex.org/C51432778","wikidata":"https://www.wikidata.org/wiki/Q1259145","display_name":"Independent component analysis","level":2,"score":0.5336716175079346},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5158218741416931},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.49572765827178955},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.43234774470329285},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4286873936653137},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4185110032558441},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4076292812824249},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3407859206199646},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.13604581356048584},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.08080348372459412},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.07673931121826172},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0730302631855011},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp.2017.8168191","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp.2017.8168191","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4099999964237213,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1790748249","https://openalex.org/W1808196926","https://openalex.org/W1836465849","https://openalex.org/W1978524241","https://openalex.org/W1987906574","https://openalex.org/W2005522781","https://openalex.org/W2006129368","https://openalex.org/W2094461119","https://openalex.org/W2096789154","https://openalex.org/W2099741732","https://openalex.org/W2100291405","https://openalex.org/W2114461480","https://openalex.org/W2119901478","https://openalex.org/W2127851351","https://openalex.org/W2130855892","https://openalex.org/W2131408671","https://openalex.org/W2135956791","https://openalex.org/W2150415460","https://openalex.org/W2188162373","https://openalex.org/W2290318471","https://openalex.org/W2401387233","https://openalex.org/W2914746235","https://openalex.org/W2949117887","https://openalex.org/W2964121744","https://openalex.org/W3124794156","https://openalex.org/W4239943352","https://openalex.org/W6686978693","https://openalex.org/W6696830301"],"related_works":["https://openalex.org/W2390344110","https://openalex.org/W2364896863","https://openalex.org/W2361066326","https://openalex.org/W2118307209","https://openalex.org/W2107364365","https://openalex.org/W1785857632","https://openalex.org/W4281722104","https://openalex.org/W2187523794","https://openalex.org/W1503525627","https://openalex.org/W1917896213"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,9,20,24,65,71,78,94,147,152],"semi-blind":[4,10,55,66,153,174],"speech":[5,17,27,43,56,87,102],"enhancement":[6],"method":[7,149],"using":[8,26],"recurrent":[11,79,171],"neural":[12],"network":[13],"(SB-RNN)":[14],"for":[15,54,109,122],"human-robot":[16],"interaction.":[18],"When":[19],"robot":[21,30,48],"interacts":[22],"with":[23],"human":[25],"signals,":[28],"the":[29,47,83,110,113,123,126,133,161,166,170],"inputs":[31],"not":[32],"only":[33],"audio":[34],"signals":[35,44,103,108,121],"recorded":[36],"by":[37,46,140],"its":[38],"own":[39],"microphone":[40],"but":[41],"also":[42,159],"made":[45],"itself,":[49],"which":[50],"can":[51],"be":[52],"used":[53,105],"enhancement.":[57],"The":[58,89,157],"SB-RNN":[59,90],"consists":[60],"of":[61,86,96,112,125,163,165],"cascaded":[62],"two":[63],"modules:":[64],"source":[67,134,175],"separation":[68,114],"module":[69,76,115],"and":[70,173],"blind":[72],"dereverberation":[73,127],"module.":[74,128],"Each":[75],"has":[77],"layer":[80],"to":[81,118,135,146],"capture":[82],"temporal":[84],"correlations":[85],"signals.":[88],"is":[91],"trained":[92],"in":[93,116],"manner":[95],"multi-task":[97,168],"learning,":[98,169],"i.e.,":[99],"isolated":[100,119],"echoic":[101],"are":[104],"as":[106],"teacher":[107],"output":[111,124],"addition":[117],"unechoic":[120],"Experimental":[129],"results":[130,158],"showed":[131,160],"that":[132],"distortion":[136],"ratio":[137],"was":[138],"improved":[139],"2.30":[141],"dB":[142],"on":[143,151],"average":[144],"compared":[145],"conventional":[148],"based":[150],"independent":[154],"component":[155],"analysis.":[156],"effectiveness":[162],"modularization":[164],"network,":[167],"structure,":[172],"separation.":[176]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}