{"id":"https://openalex.org/W1968493974","doi":"https://doi.org/10.1109/slt.2014.7078626","title":"Multichannel feature enhancement in distributed microphone arrays for robust distant speech recognition in smart rooms","display_name":"Multichannel feature enhancement in distributed microphone arrays for robust distant speech recognition in smart rooms","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W1968493974","doi":"https://doi.org/10.1109/slt.2014.7078626","mag":"1968493974"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2014.7078626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078626","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","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/A5055022808","display_name":"Seyedmahdad Mirsamadi","orcid":"https://orcid.org/0000-0002-4810-5632"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Seyedmahdad Mirsamadi","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS) The University of Texas at Dallas, Richardson, TX, U.S.A","Center for Robust Speech Systems (CRSS), The University of Texas at Dallas, Richardson, 75080-3021, U.S.A"],"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS) The University of Texas at Dallas, Richardson, TX, U.S.A","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), The University of Texas at Dallas, Richardson, 75080-3021, U.S.A","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John H.L. Hansen","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS) The University of Texas at Dallas, Richardson, TX, U.S.A","Center for Robust Speech Systems (CRSS), The University of Texas at Dallas, Richardson, 75080-3021, U.S.A"],"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS) The University of Texas at Dallas, Richardson, TX, U.S.A","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), The University of Texas at Dallas, Richardson, 75080-3021, U.S.A","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5055022808"],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":1.4557,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.81180556,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"507","last_page":"512"},"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":0.9991000294685364,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.998199999332428,"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/reverberation","display_name":"Reverberation","score":0.8811047077178955},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.7312840819358826},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7130134105682373},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6834560036659241},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6816781163215637},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5650179386138916},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.5504863262176514},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.47270891070365906},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4405823349952698},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42454245686531067},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.41488611698150635},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35393157601356506},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3310266137123108},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2629266381263733},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08228784799575806},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06840071082115173}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.8811047077178955},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.7312840819358826},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7130134105682373},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6834560036659241},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6816781163215637},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5650179386138916},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.5504863262176514},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.47270891070365906},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4405823349952698},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42454245686531067},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.41488611698150635},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35393157601356506},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3310266137123108},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2629266381263733},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08228784799575806},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06840071082115173},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/slt.2014.7078626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078626","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","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":19,"referenced_works":["https://openalex.org/W146976060","https://openalex.org/W1246381107","https://openalex.org/W1973669708","https://openalex.org/W2015143272","https://openalex.org/W2059172134","https://openalex.org/W2118595744","https://openalex.org/W2120689488","https://openalex.org/W2121973264","https://openalex.org/W2131118158","https://openalex.org/W2131968171","https://openalex.org/W2135029798","https://openalex.org/W2141520175","https://openalex.org/W2150415460","https://openalex.org/W2156855092","https://openalex.org/W2401439450","https://openalex.org/W2408656838","https://openalex.org/W3147539069","https://openalex.org/W6679607613","https://openalex.org/W6680012447"],"related_works":["https://openalex.org/W2127243424","https://openalex.org/W2037504162","https://openalex.org/W2792706544","https://openalex.org/W1568451138","https://openalex.org/W2539013788","https://openalex.org/W2156699640","https://openalex.org/W2045265907","https://openalex.org/W2972997031","https://openalex.org/W2075222291","https://openalex.org/W2900450731"],"abstract_inverted_index":{"Room":[0],"reverberation":[1,36],"and":[2,35,48,62,99],"environmental":[3],"noise":[4,34,54],"present":[5,18],"challenges":[6],"for":[7,23],"integration":[8],"of":[9,31,45,59,66,73,89],"speech":[10,60],"recognition":[11,94],"technology":[12],"in":[13,93,96],"smart":[14],"room":[15],"applications.":[16],"We":[17],"a":[19],"multichannel":[20],"enhancement":[21],"framework":[22],"distributed":[24],"microphone":[25],"arrays":[26],"to":[27,51,91],"mitigate":[28],"the":[29,77,82],"effects":[30],"both":[32,53],"additive":[33],"on":[37,76],"distant-talking":[38],"microphones.":[39],"The":[40],"proposed":[41,83],"approach":[42,84],"uses":[43],"techniques":[44],"nonnegative":[46],"matrix":[47],"tensor":[49],"factorization":[50],"achieve":[52,86],"suppression":[55],"(through":[56,64],"sparse":[57],"representation":[58],"spectra)":[61],"dereverberation":[63],"decomposition":[65],"magnitude":[67],"spectra":[68],"into":[69],"convolutive":[70],"components).":[71],"Results":[72],"ASR":[74],"experiments":[75],"DIRHA-GRID":[78],"corpus":[79],"confirm":[80],"that":[81],"can":[85],"relative":[87],"improvements":[88],"up":[90],"+20%":[92],"accuracy":[95],"highly":[97],"reverberant":[98],"noisy":[100],"conditions":[101],"using":[102],"clean-trained":[103],"models.":[104]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}