{"id":"https://openalex.org/W2407823233","doi":"https://doi.org/10.1109/icassp.2016.7472777","title":"A generative-discriminative hybrid approach to multi-channel noise reduction for robust automatic speech recognition","display_name":"A generative-discriminative hybrid approach to multi-channel noise reduction for robust automatic speech recognition","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2407823233","doi":"https://doi.org/10.1109/icassp.2016.7472777","mag":"2407823233"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472777","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472777","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 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/A5091137706","display_name":"Hendrik Meutzner","orcid":"https://orcid.org/0000-0002-5403-5642"},"institutions":[{"id":"https://openalex.org/I904495901","display_name":"Ruhr University Bochum","ror":"https://ror.org/04tsk2644","country_code":"DE","type":"education","lineage":["https://openalex.org/I904495901"]},{"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":["DE","JP"],"is_corresponding":true,"raw_author_name":"Hendrik Meutzner","raw_affiliation_strings":["Cognitive Signal Processing Group, Universit\u00e4tsstrasse 150, Bochum, Germany","NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Cognitive Signal Processing Group, Universit\u00e4tsstrasse 150, Bochum, Germany","institution_ids":["https://openalex.org/I904495901"]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, 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"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","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"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","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"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5091137706"],"corresponding_institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I904495901"],"apc_list":null,"apc_paid":null,"fwci":0.7565,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.70584733,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"5740","last_page":"5744"},"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":0.9998000264167786,"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":0.9983999729156494,"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/discriminative-model","display_name":"Discriminative model","score":0.9249042272567749},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7591840624809265},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6787296533584595},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5733417868614197},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5329163074493408},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5087581276893616},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4981672763824463},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.47991570830345154},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4705550968647003},{"id":"https://openalex.org/keywords/environmental-noise","display_name":"Environmental noise","score":0.4290877878665924},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.41368070244789124},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10047581791877747},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08856081962585449},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.06526604294776917}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.9249042272567749},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7591840624809265},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6787296533584595},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5733417868614197},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5329163074493408},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5087581276893616},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4981672763824463},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.47991570830345154},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4705550968647003},{"id":"https://openalex.org/C86781634","wikidata":"https://www.wikidata.org/wiki/Q2478325","display_name":"Environmental noise","level":3,"score":0.4290877878665924},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.41368070244789124},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10047581791877747},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08856081962585449},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.06526604294776917},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472777","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472777","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W44831635","https://openalex.org/W59508977","https://openalex.org/W84880661","https://openalex.org/W1544785557","https://openalex.org/W1576272084","https://openalex.org/W1935589317","https://openalex.org/W1981617403","https://openalex.org/W1992475611","https://openalex.org/W2018205510","https://openalex.org/W2024490156","https://openalex.org/W2042071805","https://openalex.org/W2062164080","https://openalex.org/W2126597753","https://openalex.org/W2141411743","https://openalex.org/W2160815625","https://openalex.org/W2168379380","https://openalex.org/W2288645994","https://openalex.org/W2289394825","https://openalex.org/W2394967684","https://openalex.org/W2397042577","https://openalex.org/W6601817925","https://openalex.org/W6603374476","https://openalex.org/W6660933385","https://openalex.org/W6711908631","https://openalex.org/W6712253766"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W1482209366","https://openalex.org/W2053269318","https://openalex.org/W2110523656"],"abstract_inverted_index":{"In":[0,98],"the":[1,19,36,46,136,140,154,161],"recent":[2],"years,":[3],"discriminative":[4,33],"models":[5],"have":[6],"become":[7],"a":[8,14,69,121],"very":[9],"attractive":[10],"utility":[11],"and":[12,26,35,60,114,130],"gained":[13],"lot":[15],"of":[16,38,48,128,153],"attention":[17],"in":[18,65,151],"speech":[20,49,72],"research":[21],"community,":[22],"encompassing":[23],"both":[24],"front":[25,59],"back-end":[27],"methods,":[28],"thanks":[29],"to":[30,45,67,95,110],"their":[31],"prominent":[32],"power":[34],"availability":[37],"improved":[39],"training":[40],"strategies.":[41],"When":[42],"it":[43],"comes":[44],"recognition":[47,73],"that":[50,125,135],"is":[51,145],"distorted":[52],"by":[53,119],"highly":[54],"non-stationary":[55],"environmental":[56,90],"noise,":[57,92],"robust":[58],"backend":[61],"methods":[62,84],"are":[63],"required":[64],"order":[66],"achieve":[68],"satisfactorily":[70],"high":[71],"performance.":[74],"Furthermore,":[75],"when":[76],"dealing":[77],"with":[78],"severe":[79],"noise":[80,106],"conditions,":[81],"multi-channel":[82,105],"front-end":[83],"can":[85],"be":[86],"advantageous":[87],"for":[88],"suppressing":[89],"background":[91],"as":[93,111],"compared":[94],"single-channel":[96],"methods.":[97],"this":[99],"work,":[100],"we":[101],"improve":[102],"an":[103],"existing":[104,141],"reduction":[107,158],"approach,":[108,143],"referred":[109],"DOminance-based":[112],"Loca-tional":[113],"Power-spectral":[115],"cHaracteristics":[116],"INtegration":[117],"(DOLPHIN),":[118],"using":[120],"generative-discriminative":[122],"hybrid":[123],"model,":[124],"makes":[126],"use":[127],"spatial":[129],"spectral":[131],"features.":[132],"We":[133],"show":[134],"proposed":[137],"method":[138],"outperforms":[139],"DOLPHIN":[142],"which":[144],"solely":[146],"based":[147],"on":[148,160],"generative":[149],"models,":[150],"terms":[152],"word":[155],"error":[156],"rate":[157],"achieved":[159],"CHiME-3":[162],"challenge":[163],"data.":[164]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}