{"id":"https://openalex.org/W1498991127","doi":"https://doi.org/10.1186/s13634-015-0238-6","title":"Speech recognition in reverberant and noisy environments employing multiple feature extractors and i-vector speaker adaptation","display_name":"Speech recognition in reverberant and noisy environments employing multiple feature extractors and i-vector speaker adaptation","publication_year":2015,"publication_date":"2015-06-18","ids":{"openalex":"https://openalex.org/W1498991127","doi":"https://doi.org/10.1186/s13634-015-0238-6","mag":"1498991127"},"language":"en","primary_location":{"id":"doi:10.1186/s13634-015-0238-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13634-015-0238-6","pdf_url":"https://asp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13634-015-0238-6","source":{"id":"https://openalex.org/S35920007","display_name":"EURASIP Journal on Advances in Signal Processing","issn_l":"1687-6172","issn":["1687-6172","1687-6180"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Advances in Signal Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13634-015-0238-6","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100737270","display_name":"Md. Jahangir Alam","orcid":"https://orcid.org/0000-0002-3743-9661"},"institutions":[{"id":"https://openalex.org/I4210111842","display_name":"Computer Research Institute of Montr\u00e9al","ror":"https://ror.org/0279d5115","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210111842"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Md Jahangir Alam","raw_affiliation_strings":["CRIM, Montreal, Quebec, Canada","CRIM, Montreal, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CRIM, Montreal, Quebec, Canada","institution_ids":["https://openalex.org/I4210111842"]},{"raw_affiliation_string":"CRIM, Montreal, Canada","institution_ids":["https://openalex.org/I4210111842"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114009216","display_name":"Vishwa Gupta","orcid":null},"institutions":[{"id":"https://openalex.org/I4210111842","display_name":"Computer Research Institute of Montr\u00e9al","ror":"https://ror.org/0279d5115","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210111842"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Vishwa Gupta","raw_affiliation_strings":["CRIM, Montreal, Quebec, Canada","CRIM, Montreal, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CRIM, Montreal, Quebec, Canada","institution_ids":["https://openalex.org/I4210111842"]},{"raw_affiliation_string":"CRIM, Montreal, Canada","institution_ids":["https://openalex.org/I4210111842"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036466893","display_name":"Patrick Kenny","orcid":null},"institutions":[{"id":"https://openalex.org/I4210111842","display_name":"Computer Research Institute of Montr\u00e9al","ror":"https://ror.org/0279d5115","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210111842"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Patrick Kenny","raw_affiliation_strings":["CRIM, Montreal, Quebec, Canada","CRIM, Montreal, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CRIM, Montreal, Quebec, Canada","institution_ids":["https://openalex.org/I4210111842"]},{"raw_affiliation_string":"CRIM, Montreal, Canada","institution_ids":["https://openalex.org/I4210111842"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034083532","display_name":"Pierre Dumouchel","orcid":"https://orcid.org/0000-0001-5584-4428"},"institutions":[{"id":"https://openalex.org/I9736820","display_name":"\u00c9cole de Technologie Sup\u00e9rieure","ror":"https://ror.org/0020snb74","country_code":"CA","type":"education","lineage":["https://openalex.org/I49663120","https://openalex.org/I9736820"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Pierre Dumouchel","raw_affiliation_strings":["ETS, Montreal, Quebec, Canada","ETS, Montreal, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETS, Montreal, Quebec, Canada","institution_ids":["https://openalex.org/I9736820"]},{"raw_affiliation_string":"ETS, Montreal, Canada","institution_ids":["https://openalex.org/I9736820"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100737270"],"corresponding_institution_ids":["https://openalex.org/I4210111842"],"apc_list":{"value":1140,"currency":"GBP","value_usd":1398},"apc_paid":{"value":1140,"currency":"GBP","value_usd":1398},"fwci":1.1597,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.77585414,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"2015","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.996399998664856,"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/computer-science","display_name":"Computer science","score":0.8208566904067993},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8022414445877075},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.6626244187355042},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6205683946609497},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.48993080854415894},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.4891989231109619},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.4761655032634735},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.470805287361145},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4561436176300049},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.43175289034843445},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3855352997779846},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3777168393135071},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08056628704071045}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8208566904067993},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8022414445877075},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.6626244187355042},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6205683946609497},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.48993080854415894},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.4891989231109619},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.4761655032634735},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.470805287361145},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4561436176300049},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.43175289034843445},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3855352997779846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3777168393135071},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08056628704071045},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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:10.1186/s13634-015-0238-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13634-015-0238-6","pdf_url":"https://asp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13634-015-0238-6","source":{"id":"https://openalex.org/S35920007","display_name":"EURASIP Journal on Advances in Signal Processing","issn_l":"1687-6172","issn":["1687-6172","1687-6180"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Advances in Signal Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1186/s13634-015-0238-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13634-015-0238-6","pdf_url":"https://asp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13634-015-0238-6","source":{"id":"https://openalex.org/S35920007","display_name":"EURASIP Journal on Advances in Signal Processing","issn_l":"1687-6172","issn":["1687-6172","1687-6180"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Advances in Signal Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1498991127.pdf","grobid_xml":"https://content.openalex.org/works/W1498991127.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W182365161","https://openalex.org/W1524333225","https://openalex.org/W1754457604","https://openalex.org/W1904457459","https://openalex.org/W1951896508","https://openalex.org/W1974306283","https://openalex.org/W1984541135","https://openalex.org/W1984570643","https://openalex.org/W1989314204","https://openalex.org/W1993882792","https://openalex.org/W1995190897","https://openalex.org/W2002342963","https://openalex.org/W2015633636","https://openalex.org/W2024490156","https://openalex.org/W2028124797","https://openalex.org/W2062003163","https://openalex.org/W2067111814","https://openalex.org/W2069431997","https://openalex.org/W2079623482","https://openalex.org/W2084134149","https://openalex.org/W2104780554","https://openalex.org/W2106554350","https://openalex.org/W2123832096","https://openalex.org/W2130722890","https://openalex.org/W2131342762","https://openalex.org/W2131753991","https://openalex.org/W2140046090","https://openalex.org/W2147166770","https://openalex.org/W2147768505","https://openalex.org/W2150769028","https://openalex.org/W2155722796","https://openalex.org/W2169890399","https://openalex.org/W2172097686","https://openalex.org/W2222372807","https://openalex.org/W2395750323","https://openalex.org/W2401185733","https://openalex.org/W2404874347","https://openalex.org/W2762693443","https://openalex.org/W2911394281","https://openalex.org/W2962719052","https://openalex.org/W3017143921","https://openalex.org/W4296927107","https://openalex.org/W6603795164","https://openalex.org/W6609280470"],"related_works":["https://openalex.org/W2186375278","https://openalex.org/W4255044973","https://openalex.org/W2890936991","https://openalex.org/W2499802997","https://openalex.org/W2112059504","https://openalex.org/W2727729836","https://openalex.org/W1960256358","https://openalex.org/W2548037963","https://openalex.org/W2114026179","https://openalex.org/W2464377622"],"abstract_inverted_index":{"The":[0],"REVERB":[1,186],"challenge":[2,187],"provides":[3],"a":[4,150],"common":[5],"framework":[6],"for":[7,86,252,257],"the":[8,15,59,120,129,141,174,185,191,208,247,253,258,262,266],"evaluation":[9],"of":[10,17,128,241],"feature":[11,56],"extraction":[12],"techniques":[13],"in":[14,30,37,42,149],"presence":[16],"both":[18,199],"reverberation":[19],"and":[20,68,76,113,176,203,243,249,264,272],"additive":[21],"background":[22],"noise.":[23],"State-of-the-art":[24],"speech":[25,87,97,164],"recognition":[26,88,98,165,180],"systems":[27],"perform":[28],"well":[29,45],"controlled":[31],"environments,":[32],"but":[33],"their":[34,102],"performance":[35],"degrades":[36],"realistic":[38],"acoustical":[39],"conditions,":[40],"especially":[41],"real":[43],"as":[44,46,226],"simulated":[47],"reverberant":[48],"environments.":[49],"In":[50,93,163,194,207],"this":[51],"contribution,":[52],"we":[53,100,123,153,197,236],"utilize":[54],"multiple":[55],"extractors":[57],"including":[58],"conventional":[60],"mel-filterbank,":[61,65,75],"multi-taper":[62],"spectrum":[63],"estimation-based":[64],"robust":[66],"mel":[67],"compressive":[69],"gammachirp":[70],"filterbank,":[71],"iterative":[72],"deconvolution-based":[73],"dereverberated":[74,81],"maximum":[77],"likelihood":[78],"inverse":[79],"filtering-based":[80],"mel-frequency":[82],"cepstral":[83],"coefficient":[84],"features":[85],"with":[89],"multi-condition":[90],"training":[91,175],"data.":[92],"order":[94],"to":[95,116,134,170,221,228],"improve":[96],"performance,":[99],"combine":[101],"results":[103],"using":[104,190],"ROVER":[105],"(Recognizer":[106],"Output":[107],"Voting":[108],"Error":[109],"Reduction).":[110],"For":[111],"two-":[112],"eight-channel":[114,259],"tasks,":[115],"get":[117],"benefited":[118],"from":[119,219],"multi-channel":[121],"data,":[122],"also":[124,154],"use":[125,198],"ROVER,":[126],"instead":[127],"multi-microphone":[130],"signal":[131],"processing":[132,202,213],"method,":[133],"reduce":[135,171],"word":[136,144,215],"error":[137,216],"rate":[138,217],"by":[139],"selecting":[140],"best":[142],"scoring":[143],"at":[145],"each":[146],"channel.":[147],"As":[148],"previous":[151],"work,":[152],"apply":[155],"i-vector-based":[156],"speaker":[157,167],"adaptation":[158,168],"which":[159],"was":[160],"found":[161,269],"effective.":[162],"task,":[166,210,255],"tries":[169],"mismatch":[172],"between":[173],"test":[177],"speakers.":[178],"Speech":[179],"experiments":[181],"are":[182],"conducted":[183],"on":[184,224,246,261],"2014":[188],"corpora":[189],"Kaldi":[192],"recognizer.":[193],"our":[195],"experiments,":[196],"utterance-based":[200,229],"batch":[201,205,212,230,234],"full":[204,211,233],"processing.":[206,231],"single-channel":[209],"reduced":[214],"(WER)":[218],"10.0":[220],"9.3":[222],"%":[223,245],"SimData":[225,248,263],"compared":[227],"Using":[232],"processing,":[235],"obtained":[237],"an":[238],"average":[239,267],"WER":[240],"9.0":[242],"23.4":[244],"RealData,":[250,265],"respectively,":[251],"two-channel":[254],"whereas":[256],"task":[260],"WERs":[268],"were":[270],"8.9":[271],"21.7":[273],"%,":[274],"respectively.":[275]},"counts_by_year":[{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2}],"updated_date":"2026-06-19T15:47:20.252518","created_date":"2025-10-10T00:00:00"}