{"id":"https://openalex.org/W2403535875","doi":"https://doi.org/10.1109/icassp.2016.7472922","title":"A comparative study of multi-channel processing methods for noisy automatic speech recognition in urban environments","display_name":"A comparative study of multi-channel processing methods for noisy automatic speech recognition in urban environments","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2403535875","doi":"https://doi.org/10.1109/icassp.2016.7472922","mag":"2403535875"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472922","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472922","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/A5110125670","display_name":"Tran Huy Dat","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Tran Huy Dat","raw_affiliation_strings":["Institute for Infocomm Research, A*STAR, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, A*STAR, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070417199","display_name":"Jonathan Dennis","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jonathan Dennis","raw_affiliation_strings":["Institute for Infocomm Research, A*STAR, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, A*STAR, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034549514","display_name":"Leng Yi Ren","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Leng Yi Ren","raw_affiliation_strings":["Institute for Infocomm Research, A*STAR, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, A*STAR, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008383417","display_name":"Ng Wen Zheng Terence","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ng Wen Zheng Terence","raw_affiliation_strings":["Institute for Infocomm Research, A\u2217STAR, 1 Fusionopolis Way, Singapore 138632"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, A\u2217STAR, 1 Fusionopolis Way, Singapore 138632","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5110125670"],"corresponding_institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"],"apc_list":null,"apc_paid":null,"fwci":0.2522,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.50649041,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"20","issue":null,"first_page":"6465","last_page":"6469"},"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":0.9994999766349792,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9965999722480774,"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":0.8350027799606323},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7724448442459106},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.62782883644104},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.6089435815811157},{"id":"https://openalex.org/keywords/adaptive-beamformer","display_name":"Adaptive beamformer","score":0.5912625789642334},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5699297785758972},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5263876914978027},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5154703259468079},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.46399447321891785},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4320334494113922},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42504578828811646},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36273640394210815},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.13581573963165283},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09193262457847595}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8350027799606323},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7724448442459106},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.62782883644104},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.6089435815811157},{"id":"https://openalex.org/C33378366","wikidata":"https://www.wikidata.org/wiki/Q4680719","display_name":"Adaptive beamformer","level":3,"score":0.5912625789642334},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5699297785758972},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5263876914978027},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5154703259468079},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.46399447321891785},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4320334494113922},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42504578828811646},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36273640394210815},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.13581573963165283},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09193262457847595},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/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/icassp.2016.7472922","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472922","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":"Sustainable cities and communities","score":0.8399999737739563,"id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W322920824","https://openalex.org/W1509088290","https://openalex.org/W1524333225","https://openalex.org/W1989314204","https://openalex.org/W2010362084","https://openalex.org/W2075933501","https://openalex.org/W2124558353","https://openalex.org/W2140866802","https://openalex.org/W2148613904","https://openalex.org/W2151251521","https://openalex.org/W2291864985","https://openalex.org/W2397375888","https://openalex.org/W4296927107","https://openalex.org/W6630309668","https://openalex.org/W6631362777","https://openalex.org/W6996569244"],"related_works":["https://openalex.org/W818226659","https://openalex.org/W2009075871","https://openalex.org/W2132841313","https://openalex.org/W2518591292","https://openalex.org/W2105408150","https://openalex.org/W1976800395","https://openalex.org/W2606661315","https://openalex.org/W2548445082","https://openalex.org/W2767070583","https://openalex.org/W636053046"],"abstract_inverted_index":{"For":[0],"the":[1,5,14,19,37,41,53,58,65,73,81,130,141,154,164,167],"distant":[2,66],"speech":[3,67],"recognition,":[4],"multi-channel":[6],"processing":[7,87,97],"has":[8,29],"been":[9],"proven":[10],"to":[11,18,31,115],"significantly":[12],"improve":[13],"ASR":[15],"performances":[16],"compared":[17],"single":[20],"channel":[21,127],"approaches.":[22],"However,":[23],"there":[24],"is":[25],"very":[26],"little":[27],"work":[28],"done":[30],"provide":[32],"a":[33,113],"comparative":[34],"evaluation":[35],"of":[36,83,86,88,163],"approaches,":[38],"particularly":[39],"with":[40,125],"modern":[42],"Deep":[43],"Neural":[44],"Network":[45],"(DNN)":[46],"recognizers.":[47],"In":[48],"this":[49],"paper,":[50],"we":[51,79],"address":[52],"above":[54],"problem":[55],"by":[56],"evaluating":[57],"most":[59],"recently":[60],"reported":[61],"mutti-channel":[62],"methods":[63],"for":[64,170],"recognition":[68],"under":[69],"urban":[70],"environments":[71],"using":[72],"3rd":[74],"CHiME":[75],"Challenge":[76],"database.":[77],"Particularly,":[78],"analyse":[80],"effects":[82],"each":[84],"stage":[85],"beamforming,":[89],"adaptive":[90,126],"noise":[91],"cancellation":[92],"and":[93,122,135,148,161,172],"dereverberation.":[94],"The":[95,143],"back-end":[96],"components":[98],"are":[99],"also":[100],"investigated.":[101],"We":[102],"further":[103],"describe":[104],"in":[105,129,140],"details":[106],"our":[107],"best":[108],"performing":[109],"system":[110,144],"which":[111],"combines":[112],"harmonic":[114],"subharmonic":[116],"ratio":[117],"(SHR)":[118],"voice":[119],"activity":[120],"detection,":[121],"correlative":[123],"beamforming":[124],"selection":[128],"from-end;":[131],"semi-supervised":[132],"DNN":[133],"adaptation":[134],"RNN":[136],"language":[137],"model":[138],"rescoring":[139],"back-end.":[142],"achieved":[145],"impressive":[146],"60%":[147,162],"55%":[149],"relative":[150],"WER":[151],"reductions":[152],"on":[153,166],"development":[155],"set,":[156,169],"as":[157,159],"well":[158],"65%":[160],"same":[165],"test":[168],"real":[171],"simulated":[173],"data":[174],"sets,":[175],"respectively.":[176]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}