{"id":"https://openalex.org/W2148898720","doi":"https://doi.org/10.1109/tasl.2010.2050511","title":"Reverberation Model-Based Decoding in the Logmelspec Domain for Robust Distant-Talking Speech Recognition","display_name":"Reverberation Model-Based Decoding in the Logmelspec Domain for Robust Distant-Talking Speech Recognition","publication_year":2010,"publication_date":"2010-05-26","ids":{"openalex":"https://openalex.org/W2148898720","doi":"https://doi.org/10.1109/tasl.2010.2050511","mag":"2148898720"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2010.2050511","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2010.2050511","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5057078484","display_name":"Armin Sehr","orcid":null},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Armin Sehr","raw_affiliation_strings":["Chair of Multimedia Communications and Signal Processing, University of Erlangen Nuremberg, Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chair of Multimedia Communications and Signal Processing, University of Erlangen Nuremberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090454997","display_name":"Roland Maas","orcid":null},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Roland Maas","raw_affiliation_strings":["Chair of Multimedia Communications and Signal Processing, University of Erlangen Nuremberg, Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chair of Multimedia Communications and Signal Processing, University of Erlangen Nuremberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068787682","display_name":"Walter Kellermann","orcid":"https://orcid.org/0000-0002-6501-3174"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Walter Kellermann","raw_affiliation_strings":["Chair of Multimedia Communications and Signal Processing, University of Erlangen Nuremberg, Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chair of Multimedia Communications and Signal Processing, University of Erlangen Nuremberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I181369854"],"apc_list":null,"apc_paid":null,"fwci":10.4552,"has_fulltext":false,"cited_by_count":59,"citation_normalized_percentile":{"value":0.98680203,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"18","issue":"7","first_page":"1676","last_page":"1691"},"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":0.9991000294685364,"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":0.9961000084877014,"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":0.9040960073471069},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7848077416419983},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.6951709389686584},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6940528154373169},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6785173416137695},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5381267070770264},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5097010135650635},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38554906845092773},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36441436409950256},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3317109942436218},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.20474252104759216},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1482854187488556}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.9040960073471069},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7848077416419983},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.6951709389686584},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6940528154373169},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6785173416137695},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5381267070770264},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5097010135650635},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38554906845092773},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36441436409950256},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3317109942436218},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.20474252104759216},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1482854187488556},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tasl.2010.2050511","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2010.2050511","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W7560395","https://openalex.org/W20760429","https://openalex.org/W73693705","https://openalex.org/W84068511","https://openalex.org/W1485532853","https://openalex.org/W1522463960","https://openalex.org/W1566679080","https://openalex.org/W1578856370","https://openalex.org/W1800365115","https://openalex.org/W2020127909","https://openalex.org/W2045043668","https://openalex.org/W2050693797","https://openalex.org/W2077658674","https://openalex.org/W2083212479","https://openalex.org/W2085079437","https://openalex.org/W2085151728","https://openalex.org/W2097491464","https://openalex.org/W2102072896","https://openalex.org/W2106718021","https://openalex.org/W2107992675","https://openalex.org/W2112652497","https://openalex.org/W2117678320","https://openalex.org/W2123871098","https://openalex.org/W2130283666","https://openalex.org/W2132054610","https://openalex.org/W2136821271","https://openalex.org/W2136883355","https://openalex.org/W2137075158","https://openalex.org/W2142416747","https://openalex.org/W2151484683","https://openalex.org/W2152131029","https://openalex.org/W2157515590","https://openalex.org/W2158273884","https://openalex.org/W2161784349","https://openalex.org/W2188162373","https://openalex.org/W2502655619","https://openalex.org/W4205130185","https://openalex.org/W4230562743","https://openalex.org/W4248818703","https://openalex.org/W6600294567","https://openalex.org/W6600843058","https://openalex.org/W6603089616","https://openalex.org/W6633696381","https://openalex.org/W6676684504","https://openalex.org/W6686978693"],"related_works":["https://openalex.org/W2136652457","https://openalex.org/W2169849734","https://openalex.org/W2116722627","https://openalex.org/W2129150969","https://openalex.org/W2236912844","https://openalex.org/W1975869217","https://openalex.org/W2401728283","https://openalex.org/W2383829109","https://openalex.org/W2379938888","https://openalex.org/W2849436992"],"abstract_inverted_index":{"The":[0],"REMOS":[1,94,190,201,230],"(REverberation":[2],"MOdeling":[3],"for":[4,8,38,156,171,191,215,251],"Speech":[5],"recognition)":[6],"concept":[7],"reverberation-robust":[9],"distant-talking":[10],"speech":[11,17],"recognition,":[12],"introduced":[13],"in":[14,25,32,48,69,103,146,181,232,272],"\u201cDistant-talking":[15],"continuous":[16],"recognition":[18,224],"based":[19],"on":[20,76],"a":[21,77,83,90,107,186,252,258,273],"novel":[22,164],"reverberation":[23,65,91,98,209],"model":[24,80,86,92],"the":[26,52,70,116,120,125,130,138,143,147,158,167,204,218,228,233,238,242,261],"feature":[27],"domain\u201d":[28],"(A.":[29],"Sehr":[30],",":[31],"Proc.":[33],"Interspeech,":[34],"2006,":[35],"pp.":[36],"769-772)":[37],"melspectral":[39,45],"features,":[40],"is":[41,135,150,179],"extended":[42],"to":[43,63,129,137,257],"logarithmic":[44],"(logmelspec)":[46],"features":[47,193],"this":[49,182,200],"contribution.":[50],"Thus,":[51],"favorable":[53],"properties":[54,206],"of":[55,82,106,119,166,189,199,207,220,260],"REMOS,":[56],"including":[57],"its":[58,208],"high":[59],"flexibility":[60],"with":[61,245,275,284],"respect":[62],"changing":[64],"conditions,":[66],"become":[67],"available":[68],"more":[71],"competitive":[72],"logmelspec":[73,148,192,234],"domain.":[74],"Based":[75],"combined":[78],"acoustic":[79],"consisting":[81],"hidden":[84],"Markov":[85],"(HMM)":[87],"network":[88],"and":[89,97,124,211],"(RM),":[93],"determines":[95],"clean-speech":[96],"estimates":[99,210],"during":[100],"recognition.":[101],"Therefore,":[102],"each":[104],"iteration":[105],"modified":[108],"Viterbi":[109],"algorithm,":[110],"an":[111,172],"inner":[112,160],"optimization":[113,161,177],"operation":[114,145],"maximizes":[115],"joint":[117],"density":[118],"current":[121,139],"HMM":[122],"output":[123,127],"RM":[126],"subject":[128],"constraint":[131],"that":[132,185,227],"their":[133,264],"combination":[134,144],"equal":[136],"reverberant":[140],"observation.":[141],"Since":[142],"domain":[149,235],"nonlinear,":[151],"numerical":[152],"methods":[153],"appear":[154],"necessary":[155],"solving":[157],"constrained":[159],"problem.":[162],"A":[163],"reformulation":[165],"constraint,":[168],"which":[169],"allows":[170],"efficient":[173],"solution":[174],"by":[175,248,280],"nonlinear":[176],"algorithms,":[178],"derived":[180],"paper":[183],"so":[184],"practicable":[187],"implementation":[188,202],"becomes":[194],"possible.":[195],"An":[196],"in-depth":[197],"analysis":[198],"investigates":[203],"statistical":[205],"thus":[212],"derives":[213],"possibilities":[214],"further":[216],"improving":[217],"performance":[219,265,290],"REMOS.":[221],"Connected":[222],"digit":[223],"experiments":[225],"show":[226],"proposed":[229,243],"version":[231],"significantly":[236,266],"outperforms":[237],"melspec":[239],"version.":[240],"While":[241],"RMs":[244,283],"parameters":[246],"estimated":[247],"straightforward":[249],"training":[250,281],"given":[253],"room":[254,274],"are":[255,270],"robust":[256],"mismatch":[259],"speaker-microphone":[262],"distance,":[263],"decreases":[267],"if":[268],"they":[269],"used":[271],"substantially":[276],"different":[277,295],"conditions.":[278],"However,":[279],"multi-style":[282],"data":[285],"from":[286],"several":[287],"rooms,":[288],"good":[289],"can":[291],"be":[292],"achieved":[293],"across":[294],"rooms.":[296]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":12},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":14},{"year":2012,"cited_by_count":9}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}