{"id":"https://openalex.org/W2085079437","doi":"https://doi.org/10.1109/icassp.2010.5495671","title":"Model-based dereverberation in the logmelspec domain for robust distant-talking speech recognition","display_name":"Model-based dereverberation in the logmelspec domain for robust distant-talking speech recognition","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2085079437","doi":"https://doi.org/10.1109/icassp.2010.5495671","mag":"2085079437"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5495671","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495671","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 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/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":["Multimedia Communications and Signal Processing, University of Erlangen Nuremberg, Erlangen, Germany","Multimedia Communications and Signal Processing*, University of Erlangen-Nuremberg, Cauerstr. 7, 91058, 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 Communications and Signal Processing*, University of Erlangen-Nuremberg, Cauerstr. 7, 91058, 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, University of Erlangen Nuremberg, Erlangen, Germany","Multimedia Communications and Signal Processing*, University of Erlangen-Nuremberg, Cauerstr. 7, 91058, 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 Communications and Signal Processing*, University of Erlangen-Nuremberg, Cauerstr. 7, 91058, 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, University of Erlangen Nuremberg, Erlangen, Germany","Multimedia Communications and Signal Processing*, University of Erlangen-Nuremberg, Cauerstr. 7, 91058, 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 Communications and Signal Processing*, University of Erlangen-Nuremberg, Cauerstr. 7, 91058, 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":0.6402,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.64232064,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"4298","last_page":"4301"},"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":0.9991999864578247,"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/T11698","display_name":"Underwater Acoustics Research","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/1910","display_name":"Oceanography"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.9038400053977966},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7722117900848389},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7686468362808228},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.724914014339447},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5158840417861938},{"id":"https://openalex.org/keywords/logarithm","display_name":"Logarithm","score":0.4711792767047882},{"id":"https://openalex.org/keywords/digit-recognition","display_name":"Digit recognition","score":0.43256402015686035},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.41410985589027405},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35892054438591003},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.35188090801239014},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.32988759875297546},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1743340790271759},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09752938151359558}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.9038400053977966},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7722117900848389},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7686468362808228},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.724914014339447},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5158840417861938},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.4711792767047882},{"id":"https://openalex.org/C2984784707","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Digit recognition","level":3,"score":0.43256402015686035},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.41410985589027405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35892054438591003},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.35188090801239014},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.32988759875297546},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1743340790271759},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09752938151359558},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2010.5495671","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495671","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.205.4542","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.205.4542","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.lnt.de/lms/publications/web/lnt2010_13.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W20760429","https://openalex.org/W73693705","https://openalex.org/W84068511","https://openalex.org/W1573570773","https://openalex.org/W2020127909","https://openalex.org/W2045036776","https://openalex.org/W2050693797","https://openalex.org/W2077658674","https://openalex.org/W2112652497","https://openalex.org/W2123871098","https://openalex.org/W2146871184","https://openalex.org/W2502655619","https://openalex.org/W6600843058","https://openalex.org/W6603089616","https://openalex.org/W6634340323","https://openalex.org/W6676684504"],"related_works":["https://openalex.org/W2107304307","https://openalex.org/W2121652828","https://openalex.org/W3033124456","https://openalex.org/W2992378684","https://openalex.org/W2964829415","https://openalex.org/W2122233706","https://openalex.org/W642007152","https://openalex.org/W2105439218","https://openalex.org/W2686775474","https://openalex.org/W2131711534"],"abstract_inverted_index":{"The":[0],"REMOS":[1,45,87,101],"(REverberation":[2],"MOdeling":[3],"for":[4,8,15,65,88],"Speech":[5],"recognition)":[6],"concept":[7],"reverberation-robust":[9],"distant-talking":[10],"speech":[11],"recognition,":[12],"introduced":[13],"in":[14,20,78,107],"melspectral":[16,25],"features,":[17,67],"is":[18,76],"extended":[19],"this":[21,61,79],"contribution":[22],"to":[23],"logarithmic":[24],"(logmelspec)":[26],"features.":[27],"Based":[28],"on":[29],"a":[30,36,42],"combined":[31],"acoustic":[32],"model":[33,39],"consisting":[34],"of":[35,60,86],"hidden":[37],"Markov":[38],"network":[40],"and":[41,48],"reverberation":[43,49],"model,":[44],"determines":[46],"clean-speech":[47],"estimates":[50],"during":[51],"recognition":[52,95],"by":[53,72],"an":[54,69,83],"inner":[55,62],"optimization":[56,63,74],"operation.":[57],"A":[58],"reformulation":[59],"problem":[64],"logmelspec":[66,89],"allowing":[68],"efficient":[70,84],"solution":[71],"nonlinear":[73],"algorithms,":[75],"derived":[77],"paper":[80],"so":[81],"that":[82,98],"implementation":[85,102],"features":[90],"becomes":[91],"possible.":[92],"Connected":[93],"digit":[94],"experiments":[96],"show":[97],"the":[99],"proposed":[100],"significantly":[103],"outperforms":[104],"reverberantly-trained":[105],"HMMs":[106],"highly":[108],"reverberant":[109],"environments.":[110]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}