{"id":"https://openalex.org/W2008146117","doi":"https://doi.org/10.1109/hscma.2014.6843275","title":"Efficient training of acoustic models for reverberation-robust medium-vocabulary automatic speech recognition","display_name":"Efficient training of acoustic models for reverberation-robust medium-vocabulary automatic speech recognition","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2008146117","doi":"https://doi.org/10.1109/hscma.2014.6843275","mag":"2008146117"},"language":"en","primary_location":{"id":"doi:10.1109/hscma.2014.6843275","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hscma.2014.6843275","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 4th Joint Workshop on Hands-free Speech Communication and Microphone Arrays (HSCMA)","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/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, 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, Germany","institution_ids":["https://openalex.org/I129643931"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018357812","display_name":"Hendrik Barfuss","orcid":"https://orcid.org/0000-0001-7510-7660"},"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":"Hendrik Barfuss","raw_affiliation_strings":["Multimedia Communications and Signal Processing, Friedrich-Alexander-University of Erlangen-Nuremberg, Erlangen, Germany","Multimedia Commun. & Signal Process., Friedrich-Alexander-Univ. of Erlangen-Nuremberg, Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Communications and Signal Processing, Friedrich-Alexander-University of Erlangen-Nuremberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]},{"raw_affiliation_string":"Multimedia Commun. & Signal Process., Friedrich-Alexander-Univ. of Erlangen-Nuremberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021451799","display_name":"Christian Hofmann","orcid":"https://orcid.org/0000-0002-2216-0211"},"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":"Christian Hofmann","raw_affiliation_strings":["Multimedia Communications and Signal Processing, Friedrich-Alexander-University of Erlangen-Nuremberg, Erlangen, Germany","Multimedia Commun. & Signal Process., Friedrich-Alexander-Univ. of Erlangen-Nuremberg, Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Communications and Signal Processing, Friedrich-Alexander-University of Erlangen-Nuremberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]},{"raw_affiliation_string":"Multimedia Commun. & Signal Process., Friedrich-Alexander-Univ. 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":["Multimedia Communications and Signal Processing, Friedrich-Alexander-University of Erlangen-Nuremberg, Erlangen, Germany","Multimedia Commun. & Signal Process., Friedrich-Alexander-Univ. of Erlangen-Nuremberg, Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Communications and Signal Processing, Friedrich-Alexander-University of Erlangen-Nuremberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]},{"raw_affiliation_string":"Multimedia Commun. & Signal Process., Friedrich-Alexander-Univ. 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":["Multimedia Communications and Signal Processing, Friedrich-Alexander-University of Erlangen-Nuremberg, Erlangen, Germany","Multimedia Commun. & Signal Process., Friedrich-Alexander-Univ. of Erlangen-Nuremberg, Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Communications and Signal Processing, Friedrich-Alexander-University of Erlangen-Nuremberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]},{"raw_affiliation_string":"Multimedia Commun. & Signal Process., Friedrich-Alexander-Univ. of Erlangen-Nuremberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2068,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.44974265,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"39","issue":null,"first_page":"177","last_page":"181"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/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/T11309","display_name":"Music and Audio Processing","score":0.9986000061035156,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8158414959907532},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7840983867645264},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7597767114639282},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.7054585814476013},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6291822791099548},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.6244243383407593},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5754116177558899},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.476910799741745},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43318796157836914},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.43222230672836304},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4175465404987335},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.279010534286499},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1741611659526825},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08114898204803467},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.07611986994743347}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8158414959907532},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7840983867645264},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7597767114639282},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.7054585814476013},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6291822791099548},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.6244243383407593},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5754116177558899},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.476910799741745},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43318796157836914},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.43222230672836304},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4175465404987335},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.279010534286499},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1741611659526825},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08114898204803467},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.07611986994743347},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hscma.2014.6843275","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hscma.2014.6843275","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 4th Joint Workshop on Hands-free Speech Communication and Microphone Arrays (HSCMA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W47839664","https://openalex.org/W84880661","https://openalex.org/W172635372","https://openalex.org/W206545267","https://openalex.org/W1578856370","https://openalex.org/W1973669708","https://openalex.org/W1990063583","https://openalex.org/W2024490156","https://openalex.org/W2026063171","https://openalex.org/W2049633694","https://openalex.org/W2077574412","https://openalex.org/W2125471631","https://openalex.org/W2136439176","https://openalex.org/W2145982029","https://openalex.org/W2147706354","https://openalex.org/W2148575186","https://openalex.org/W2148898720","https://openalex.org/W2158273884","https://openalex.org/W2164502538","https://openalex.org/W2489311264","https://openalex.org/W2490695385","https://openalex.org/W3129711340","https://openalex.org/W4205130185","https://openalex.org/W4248818703","https://openalex.org/W6603374476","https://openalex.org/W6678651673","https://openalex.org/W6681351234"],"related_works":["https://openalex.org/W1656519308","https://openalex.org/W2042717753","https://openalex.org/W2022849831","https://openalex.org/W2037265366","https://openalex.org/W2026603686","https://openalex.org/W2121652828","https://openalex.org/W2186896963","https://openalex.org/W4372346152","https://openalex.org/W4361192867","https://openalex.org/W2161511440"],"abstract_inverted_index":{"A":[0],"recently":[1],"proposed":[2],"concept":[3],"for":[4,9,46,54,97,115,131],"training":[5,79],"reverberation-robust":[6],"acoustic":[7,106,126],"models":[8,24,28,107],"automatic":[10],"speech":[11],"recognition":[12,122],"using":[13],"pairs":[14],"of":[15,35,57,72],"clean":[16,44],"and":[17,50,99],"reverberant":[18,52],"data":[19,45,53],"is":[20,40,81,90],"extended":[21],"from":[22],"word":[23,88],"to":[25,41,119],"tied-state":[26,75],"triphone":[27],"in":[29],"this":[30],"paper.":[31],"The":[32],"key":[33],"idea":[34],"the":[36,43,47,51,55,58,63,70,78,87,93,105,116],"concept,":[37],"termed":[38],"ICEWIND,":[39],"use":[42],"temporal":[48],"alignment":[49],"estimation":[56],"emission":[59,117],"densities.":[60],"Experiments":[61],"with":[62,74,109],"5000-word":[64],"Wall":[65],"Street":[66],"Journal":[67],"corpus":[68],"confirm":[69],"benefits":[71],"ICEWIND":[73,110,128],"triphones:":[76],"While":[77],"time":[80],"reduced":[82,133],"by":[83],"more":[84],"than":[85],"90%,":[86],"accuracy":[89],"improved":[91],"at":[92],"same":[94],"time,":[95],"both":[96],"room-specific":[98],"multi-style":[100],"hidden":[101],"Markov":[102],"models.":[103],"Since":[104],"trained":[108],"need":[111],"less":[112],"Gaussian":[113],"components":[114],"densities":[118],"achieve":[120],"comparable":[121],"rates":[123],"as":[124],"Baum-Welch":[125],"models,":[127],"also":[129],"allows":[130],"a":[132],"decoding":[134],"complexity.":[135]},"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}