{"id":"https://openalex.org/W2006540521","doi":"https://doi.org/10.1109/icassp.2013.6639098","title":"An uncertainty decoding approach to noise- and reverberation-robust speech recognition","display_name":"An uncertainty decoding approach to noise- and reverberation-robust speech recognition","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2006540521","doi":"https://doi.org/10.1109/icassp.2013.6639098","mag":"2006540521"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639098","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639098","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","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/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":["Multimedia Communications and Signal Processing, University of Erlangen-Nuremberg, Erlangen, Germany","[Multimedia Commun. & Signal Process., Univ. of Erlangen-Nuremberg, Erlangen, Germany]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Communications and Signal Processing, University of Erlangen-Nuremberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]},{"raw_affiliation_string":"[Multimedia Commun. & Signal Process., Univ. of Erlangen-Nuremberg, Erlangen, Germany]","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054898715","display_name":"Akshaya Thippur","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Akshaya Thippur","raw_affiliation_strings":["Computer Vision and Active Perception Laboratory, School of Computer Science and Communication, KTH Royal Institute of Technology, Stockholm, Sweden","Sch. of Comput. Sci. & Commun., KTH R. Inst. of Technol., Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Vision and Active Perception Laboratory, School of Computer Science and Communication, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Sch. of Comput. Sci. & Commun., KTH R. Inst. of Technol., Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057078484","display_name":"Armin Sehr","orcid":null},"institutions":[{"id":"https://openalex.org/I129643931","display_name":"Berliner Hochschule f\u00fcr Technik","ror":"https://ror.org/00w7whj55","country_code":"DE","type":"education","lineage":["https://openalex.org/I129643931"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Armin Sehr","raw_affiliation_strings":["Department VII, Beuth University of Applied Sciences, Berlin, Germany","Dept. VII, Beuth Univ. of Appl. Sci. Berlin, Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department VII, Beuth University of Applied Sciences, Berlin, Germany","institution_ids":["https://openalex.org/I129643931"]},{"raw_affiliation_string":"Dept. VII, Beuth Univ. of Appl. Sci. Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I129643931"]}]},{"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":["Multimedia Communications and Signal Processing, University of Erlangen-Nuremberg, Erlangen, Germany","[Multimedia Commun. & Signal Process., Univ. of Erlangen-Nuremberg, Erlangen, Germany]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Communications and Signal Processing, University of Erlangen-Nuremberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]},{"raw_affiliation_string":"[Multimedia Commun. & Signal Process., Univ. of Erlangen-Nuremberg, Erlangen, Germany]","institution_ids":["https://openalex.org/I181369854"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2348,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.39084967,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"2","issue":null,"first_page":"7388","last_page":"7392"},"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":0.9987999796867371,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9980000257492065,"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":0.8546048402786255},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6199933886528015},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6153014302253723},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6024522185325623},{"id":"https://openalex.org/keywords/piecewise","display_name":"Piecewise","score":0.6021509170532227},{"id":"https://openalex.org/keywords/independence","display_name":"Independence (probability theory)","score":0.5327624678611755},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5294221043586731},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5105975270271301},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.4501282870769501},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.42109215259552},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.41799864172935486},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37116512656211853},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3255048394203186},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29685071110725403},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2846037745475769},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.15938779711723328},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08033370971679688}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.8546048402786255},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6199933886528015},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6153014302253723},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6024522185325623},{"id":"https://openalex.org/C164660894","wikidata":"https://www.wikidata.org/wiki/Q2037833","display_name":"Piecewise","level":2,"score":0.6021509170532227},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.5327624678611755},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5294221043586731},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5105975270271301},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.4501282870769501},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.42109215259552},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.41799864172935486},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37116512656211853},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3255048394203186},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29685071110725403},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2846037745475769},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.15938779711723328},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08033370971679688},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2013.6639098","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639098","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W30237829","https://openalex.org/W76514835","https://openalex.org/W1506806321","https://openalex.org/W1904133584","https://openalex.org/W1973669708","https://openalex.org/W1991053228","https://openalex.org/W2002342963","https://openalex.org/W2004290271","https://openalex.org/W2009106392","https://openalex.org/W2037740282","https://openalex.org/W2050693797","https://openalex.org/W2058341666","https://openalex.org/W2087945031","https://openalex.org/W2109754985","https://openalex.org/W2112363360","https://openalex.org/W2117518720","https://openalex.org/W2132054610","https://openalex.org/W2142352807","https://openalex.org/W2148898720","https://openalex.org/W2149390258","https://openalex.org/W2152131029","https://openalex.org/W2165534711","https://openalex.org/W2170317095","https://openalex.org/W2404226287","https://openalex.org/W2489311264","https://openalex.org/W6601235113","https://openalex.org/W6685223674","https://openalex.org/W6713516389"],"related_works":["https://openalex.org/W1656519308","https://openalex.org/W2042717753","https://openalex.org/W2037265366","https://openalex.org/W2022849831","https://openalex.org/W2391832549","https://openalex.org/W2286653370","https://openalex.org/W1499578372","https://openalex.org/W2368849850","https://openalex.org/W2053269318","https://openalex.org/W1799937301"],"abstract_inverted_index":{"The":[0,70],"generic":[1],"REMOS":[2,21,104],"(REverberation":[3],"MOdeling":[4],"for":[5,40,72,81],"robust":[6],"Speech":[7],"recognition)":[8],"concept":[9],"is":[10,51],"extended":[11],"in":[12,55,105],"this":[13],"contribution":[14],"to":[15,34,52,57,65],"cope":[16],"with":[17,127],"additional":[18,73],"noise":[19,74],"components.":[20],"originally":[22],"embeds":[23],"an":[24,88,117],"explicit":[25,118],"reverberation":[26,68,119],"model":[27,31],"into":[28],"a":[29,35,47,77],"hiddenMarkov":[30],"(HMM)":[32],"leading":[33],"relaxed":[36],"conditional":[37,123],"independence":[38,124],"assumption":[39],"the":[41,59,66,82,101,114,122],"observed":[42],"feature":[43],"vectors.":[44],"During":[45],"recognition,":[46],"nonlinear":[48,83],"optimization":[49,84],"problem":[50],"be":[53],"solved":[54],"order":[56],"adapt":[58],"HMMs'":[60],"output":[61],"probability":[62],"density":[63],"functions":[64],"current":[67],"conditions.":[69],"extension":[71],"components":[75],"necessitates":[76],"modified":[78],"numerical":[79],"solver":[80],"problem.":[85],"We":[86],"propose":[87],"approximation":[89],"scheme":[90],"based":[91],"on":[92],"continuous":[93],"piecewise":[94],"linear":[95],"regression.":[96],"Connected-digit":[97],"recognition":[98],"experiments":[99],"demonstrate":[100],"potential":[102],"of":[103,116],"reverberant":[106],"and":[107],"noisy":[108],"environments.":[109],"They":[110],"furthermore":[111],"reveal":[112],"that":[113],"benefit":[115],"model,":[120],"overcoming":[121],"assumption,":[125],"increases":[126],"increasing":[128],"signal-to-noise-ratios.":[129]},"counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}