{"id":"https://openalex.org/W2291864985","doi":"https://doi.org/10.1109/asru.2015.7404839","title":"Single and multi-channel approaches for distant speech recognition under noisy reverberant conditions: I2R'S system description for the ASpIRE challenge","display_name":"Single and multi-channel approaches for distant speech recognition under noisy reverberant conditions: I2R'S system description for the ASpIRE challenge","publication_year":2015,"publication_date":"2015-12-01","ids":{"openalex":"https://openalex.org/W2291864985","doi":"https://doi.org/10.1109/asru.2015.7404839","mag":"2291864985"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2015.7404839","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2015.7404839","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":"conference-paper","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/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"],"raw_orcid":null,"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/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":false,"raw_author_name":"Tran Huy Dat","raw_affiliation_strings":["Institute for Infocomm Research, A*STAR, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, A*STAR, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"518","last_page":"524"},"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":0.9994000196456909,"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":0.9988999962806702,"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":0.7566779851913452},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7536044120788574},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6658609509468079},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6004906296730042},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5642574429512024},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.494005024433136},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.4817828834056854},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4700015187263489},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45868635177612305},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4427068531513214},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.4319629967212677},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40040427446365356},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34300297498703003},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17244300246238708},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11740845441818237},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09757852554321289},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.08412995934486389}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7566779851913452},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7536044120788574},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6658609509468079},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6004906296730042},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5642574429512024},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.494005024433136},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.4817828834056854},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4700015187263489},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45868635177612305},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4427068531513214},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.4319629967212677},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40040427446365356},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34300297498703003},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17244300246238708},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11740845441818237},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09757852554321289},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.08412995934486389},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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/asru.2015.7404839","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2015.7404839","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":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W97072897","https://openalex.org/W1524333225","https://openalex.org/W1808196926","https://openalex.org/W1984196678","https://openalex.org/W2010362084","https://openalex.org/W2046317813","https://openalex.org/W2124558353","https://openalex.org/W2131342762","https://openalex.org/W2137867936","https://openalex.org/W2148613904","https://openalex.org/W2150384167","https://openalex.org/W2151251521","https://openalex.org/W2188082611","https://openalex.org/W2397375888","https://openalex.org/W4285719527","https://openalex.org/W6603931906","https://openalex.org/W6631362777","https://openalex.org/W6687200282","https://openalex.org/W6996569244"],"related_works":["https://openalex.org/W1562475690","https://openalex.org/W1488529827","https://openalex.org/W4389082013","https://openalex.org/W1879255185","https://openalex.org/W2120442551","https://openalex.org/W2769861442","https://openalex.org/W1980506188","https://openalex.org/W2900122540","https://openalex.org/W4240587264","https://openalex.org/W2011788874"],"abstract_inverted_index":{"In":[0,22],"this":[1],"paper,":[2],"we":[3],"introduce":[4],"the":[5,9,17,30,69,106,111,125,130,145],"system":[6,31,36,115,134],"developed":[7],"at":[8],"Institute":[10],"for":[11,16],"Infocomm":[12],"Research":[13],"(I2":[14],"R)":[15],"ASpIRE":[18],"(Automatic":[19],"Speech":[20],"recognition":[21],"Reverberant":[23],"Environments)":[24],"challenge.":[25],"The":[26,73],"main":[27],"components":[28],"of":[29,38,77,122,127,140,149],"are":[32],"a":[33,39,50,55,59,78,92,117],"front-end":[34],"processing":[35],"consisting":[37],"distributed":[40],"beam-forming":[41],"algorithm,":[42],"that":[43,85,95],"performs":[44,96],"adaptive":[45],"weighting":[46],"and":[47,58],"channel":[48],"elimination,":[49],"speech":[51],"dereverberation":[52],"approach":[53],"using":[54,68,101],"maximum-kurtosis":[56],"criteria,":[57],"robust":[60],"voice":[61],"activity":[62],"detection":[63],"(VAD)":[64],"module":[65],"based":[66],"on":[67,129],"sub-harmonic":[70],"ratio":[71],"(SHR).":[72],"acoustic":[74],"back-end":[75],"consists":[76],"multi-conditional":[79],"Deep":[80],"Neural":[81],"Network":[82],"(DNN)":[83],"model":[84,99],"uses":[86],"speaker":[87],"adapted":[88],"features":[89],"combined":[90],"with":[91],"decoding":[93,108],"strategy":[94],"semi-supervised":[97],"DNN":[98],"adaptation":[100],"weighted":[102],"labels":[103],"generated":[104],"by":[105],"first-pass":[107],"output.":[109],"On":[110],"single-microphone":[112],"evaluation,":[113,132],"our":[114,133],"achieved":[116,135],"word":[118],"error":[119],"rate":[120],"(WER)":[121],"44.8%.":[123],"With":[124],"incorporation":[126],"beamforming":[128],"multi-microphone":[131],"an":[136],"improvement":[137],"in":[138],"WER":[139],"over":[141],"6%":[142],"to":[143],"give":[144],"best":[146],"evaluation":[147],"result":[148],"38.5%.":[150]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}