{"id":"https://openalex.org/W2018205510","doi":"https://doi.org/10.1109/tasl.2013.2277937","title":"Dominance Based Integration of Spatial and Spectral Features for Speech Enhancement","display_name":"Dominance Based Integration of Spatial and Spectral Features for Speech Enhancement","publication_year":2013,"publication_date":"2013-08-15","ids":{"openalex":"https://openalex.org/W2018205510","doi":"https://doi.org/10.1109/tasl.2013.2277937","mag":"2018205510"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2013.2277937","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2013.2277937","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"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":"Tomohiro Nakatani","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","NTT Commun. Sci. Lab., NTT Corp., Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Commun. Sci. Lab., NTT Corp., Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009309584","display_name":"Shoko Araki","orcid":"https://orcid.org/0000-0003-4363-4305"},"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":"Shoko Araki","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","NTT Commun. Sci. Lab., NTT Corp., Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Commun. Sci. Lab., NTT Corp., Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101618071","display_name":"Takuya Yoshioka","orcid":"https://orcid.org/0009-0003-7791-3545"},"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":"Takuya Yoshioka","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","NTT Commun. Sci. Lab., NTT Corp., Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Commun. Sci. Lab., NTT Corp., Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"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":"Marc Delcroix","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","NTT Commun. Sci. Lab., NTT Corp., Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Commun. Sci. Lab., NTT Corp., Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109368288","display_name":"Masakiyo Fujimoto","orcid":null},"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":"Masakiyo Fujimoto","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","NTT Commun. Sci. Lab., NTT Corp., Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Commun. Sci. Lab., NTT Corp., Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":4.7615,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.95350068,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"21","issue":"12","first_page":"2516","last_page":"2531"},"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/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"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7143751382827759},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6582092046737671},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6103017330169678},{"id":"https://openalex.org/keywords/interference","display_name":"Interference (communication)","score":0.5047727823257446},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5041137933731079},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4903414249420166},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4745548367500305},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.46249982714653015},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.46105945110321045},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.26074132323265076},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.07642573118209839}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7143751382827759},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6582092046737671},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6103017330169678},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.5047727823257446},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5041137933731079},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4903414249420166},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4745548367500305},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.46249982714653015},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.46105945110321045},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26074132323265076},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.07642573118209839},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tasl.2013.2277937","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2013.2277937","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W21035339","https://openalex.org/W37526647","https://openalex.org/W44831635","https://openalex.org/W173561343","https://openalex.org/W1898225171","https://openalex.org/W1967916528","https://openalex.org/W1984196678","https://openalex.org/W1987906574","https://openalex.org/W1989954041","https://openalex.org/W1991082011","https://openalex.org/W1996837089","https://openalex.org/W2000431869","https://openalex.org/W2005733316","https://openalex.org/W2029564985","https://openalex.org/W2031583051","https://openalex.org/W2043216213","https://openalex.org/W2060778387","https://openalex.org/W2070707809","https://openalex.org/W2097242476","https://openalex.org/W2109258319","https://openalex.org/W2111208321","https://openalex.org/W2120608389","https://openalex.org/W2126597753","https://openalex.org/W2127671620","https://openalex.org/W2130322773","https://openalex.org/W2138889249","https://openalex.org/W2146871184","https://openalex.org/W2151046798","https://openalex.org/W2152488273","https://openalex.org/W2167152389","https://openalex.org/W2396455701","https://openalex.org/W3147539069","https://openalex.org/W4205778870","https://openalex.org/W6601563604","https://openalex.org/W6601817925","https://openalex.org/W6607114211"],"related_works":["https://openalex.org/W2349769824","https://openalex.org/W2914532148","https://openalex.org/W2372625757","https://openalex.org/W4313178214","https://openalex.org/W2970653563","https://openalex.org/W3093766508","https://openalex.org/W2012393389","https://openalex.org/W2899717399","https://openalex.org/W3165027275","https://openalex.org/W2380525500"],"abstract_inverted_index":{"This":[0,83],"paper":[1,84],"proposes":[2,86],"a":[3,13,19],"versatile":[4],"technique":[5,136],"for":[6,56,91],"integrating":[7],"two":[8,28,62],"conventional":[9,43],"speech":[10,57,73,141,146],"enhancement":[11],"approaches,":[12],"spatial":[14,34],"clustering":[15],"approach":[16,22],"(SCA)":[17],"and":[18,35,68,109,122,129,143],"factorial":[20],"model":[21],"(FMA),":[23],"which":[24],"are":[25,52],"based":[26,104],"on":[27,105],"different":[29],"features":[30],"of":[31,60,88,94],"signals,":[32],"namely":[33],"spectral":[36,102,124],"features,":[37],"respectively.":[38],"When":[39],"used":[40],"separately":[41],"the":[42,61,89,95,123,134,144],"approaches":[44,63],"simply":[45],"identify":[46],"time":[47],"frequency":[48],"(TF)":[49],"bins":[50],"that":[51,100,133],"dominated":[53],"by":[54],"interference":[55,81],"enhancement.":[58],"Integration":[59],"makes":[64],"identification":[65],"more":[66,75],"reliable,":[67],"allows":[69],"us":[70],"to":[71,111],"estimate":[72],"spectra":[74],"accurately":[76],"even":[77],"in":[78],"highly":[79],"nonstationary":[80],"environments.":[82],"also":[85],"extensions":[87],"FMA":[90],"further":[92],"elaboration":[93],"proposed":[96,135],"technique,":[97],"including":[98],"one":[99],"uses":[101],"models":[103],"mel-frequency":[106],"cepstral":[107],"coefficients":[108],"another":[110],"cope":[112],"with":[113],"mismatches,":[114,118],"such":[115],"as":[116],"channel":[117],"between":[119],"captured":[120],"signals":[121],"models.":[125],"Experiments":[126],"using":[127],"simulated":[128],"real":[130],"recordings":[131],"show":[132],"can":[137],"effectively":[138],"improve":[139],"audible":[140],"quality":[142],"automatic":[145],"recognition":[147],"score.":[148]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}