{"id":"https://openalex.org/W2290466121","doi":"https://doi.org/10.1109/asru.2015.7404823","title":"Adaptive beamforming and adaptive training of DNN acoustic models for enhanced multichannel noisy speech recognition","display_name":"Adaptive beamforming and adaptive training of DNN acoustic models for enhanced multichannel noisy speech recognition","publication_year":2015,"publication_date":"2015-12-01","ids":{"openalex":"https://openalex.org/W2290466121","doi":"https://doi.org/10.1109/asru.2015.7404823","mag":"2290466121"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2015.7404823","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2015.7404823","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","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/A5007071179","display_name":"Alexey Prudnikov","orcid":null},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Alexey Prudnikov","raw_affiliation_strings":["ITMO University, Saint-Petersburg, Russia","Speech Technology Center Inc"],"affiliations":[{"raw_affiliation_string":"ITMO University, Saint-Petersburg, Russia","institution_ids":["https://openalex.org/I173089394"]},{"raw_affiliation_string":"Speech Technology Center Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014394261","display_name":"Maxim Korenevsky","orcid":null},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Maxim Korenevsky","raw_affiliation_strings":["ITMO University, Saint-Petersburg, Russia","STC-Innovations Inc"],"affiliations":[{"raw_affiliation_string":"ITMO University, Saint-Petersburg, Russia","institution_ids":["https://openalex.org/I173089394"]},{"raw_affiliation_string":"STC-Innovations Inc","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029647018","display_name":"Sergei Aleinik","orcid":null},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Sergei Aleinik","raw_affiliation_strings":["ITMO University, Saint-Petersburg, Russia"],"affiliations":[{"raw_affiliation_string":"ITMO University, Saint-Petersburg, Russia","institution_ids":["https://openalex.org/I173089394"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5007071179"],"corresponding_institution_ids":["https://openalex.org/I173089394"],"apc_list":null,"apc_paid":null,"fwci":2.5847,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.90741604,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"51","issue":null,"first_page":"401","last_page":"408"},"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":0.9997000098228455,"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":0.9987999796867371,"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/speech-recognition","display_name":"Speech recognition","score":0.8030753135681152},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7886292934417725},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.7413787841796875},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7272312641143799},{"id":"https://openalex.org/keywords/adaptive-beamformer","display_name":"Adaptive beamformer","score":0.6770282983779907},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5976514220237732},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.48091980814933777},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4591902792453766},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.44492626190185547},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.43029719591140747},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.42141276597976685},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4169127941131592},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37649664282798767},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3365122377872467},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09948676824569702}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8030753135681152},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7886292934417725},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.7413787841796875},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7272312641143799},{"id":"https://openalex.org/C33378366","wikidata":"https://www.wikidata.org/wiki/Q4680719","display_name":"Adaptive beamformer","level":3,"score":0.6770282983779907},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5976514220237732},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.48091980814933777},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4591902792453766},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.44492626190185547},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.43029719591140747},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.42141276597976685},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4169127941131592},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37649664282798767},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3365122377872467},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09948676824569702},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/asru.2015.7404823","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2015.7404823","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W111477576","https://openalex.org/W142257298","https://openalex.org/W653761051","https://openalex.org/W1524333225","https://openalex.org/W1904457459","https://openalex.org/W1910023617","https://openalex.org/W1985371235","https://openalex.org/W2002342963","https://openalex.org/W2005602327","https://openalex.org/W2032647955","https://openalex.org/W2039057510","https://openalex.org/W2052667477","https://openalex.org/W2061074721","https://openalex.org/W2066218102","https://openalex.org/W2079623482","https://openalex.org/W2099655464","https://openalex.org/W2109603768","https://openalex.org/W2114719288","https://openalex.org/W2121973264","https://openalex.org/W2124541940","https://openalex.org/W2131342762","https://openalex.org/W2158072351","https://openalex.org/W2216943681","https://openalex.org/W2289394825","https://openalex.org/W2402626018","https://openalex.org/W2539797148","https://openalex.org/W3147539069","https://openalex.org/W6604441197","https://openalex.org/W6631362777","https://openalex.org/W6650992335","https://openalex.org/W6674981436","https://openalex.org/W6679429981","https://openalex.org/W6712908891","https://openalex.org/W6728770099"],"related_works":["https://openalex.org/W2767070583","https://openalex.org/W2784052451","https://openalex.org/W2348931051","https://openalex.org/W1999699871","https://openalex.org/W4225124612","https://openalex.org/W2043806667","https://openalex.org/W2021633306","https://openalex.org/W2006801911","https://openalex.org/W2033669961","https://openalex.org/W2971899271"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"our":[3,61],"contribution":[4],"to":[5,81],"the":[6,13,67,74,82],"development":[7,68],"of":[8,24],"an":[9,37],"ASR":[10],"system":[11,62],"for":[12,27,44,53],"CHiME":[14],"2015":[15],"Challenge.":[16],"We":[17],"applied":[18],"a":[19,59],"new":[20],"adaptive":[21],"beamforming":[22],"method":[23],"multichannel":[25],"alignment":[26],"enhancing":[28],"speech":[29],"recorded":[30],"with":[31],"six":[32],"microphones.":[33],"Then":[34],"we":[35],"trained":[36],"effective":[38],"CD-DNN-HMM":[39],"acoustic":[40],"model":[41],"using":[42],"CMVN":[43],"noise":[45],"robustness":[46],"as":[47,49],"well":[48],"fMLLR":[50],"and":[51,55,70],"i-vectors":[52],"speaker":[54],"environment":[56],"adaptation.":[57],"As":[58],"result,":[60],"provides":[63],"7.33%":[64],"WER":[65,72,78],"on":[66,73],"set":[69,76],"14.34%":[71],"test":[75],"(58%":[77],"reduction":[79],"compared":[80],"baseline":[83],"system).":[84]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}