{"id":"https://openalex.org/W2022111326","doi":"https://doi.org/10.1109/icassp.2009.4960436","title":"Strategies for modeling reverberant speech in the feature domain","display_name":"Strategies for modeling reverberant speech in the feature domain","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2022111326","doi":"https://doi.org/10.1109/icassp.2009.4960436","mag":"2022111326"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960436","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960436","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 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":"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":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.08176796,"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":"3725","last_page":"3728"},"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":0.9986000061035156,"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":0.9929999709129333,"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":0.8981729745864868},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7179723978042603},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6949208974838257},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6571921706199646},{"id":"https://openalex.org/keywords/impulse-response","display_name":"Impulse response","score":0.5430916547775269},{"id":"https://openalex.org/keywords/impulse","display_name":"Impulse (physics)","score":0.524692952632904},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5117999911308289},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.5039395689964294},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48576000332832336},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4373902380466461},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.4131702780723572},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.39875325560569763},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27988481521606445},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09581431746482849},{"id":"https://openalex.org/keywords/sound-pressure","display_name":"Sound pressure","score":0.08160984516143799},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07744666934013367},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06453248858451843}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.8981729745864868},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7179723978042603},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6949208974838257},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6571921706199646},{"id":"https://openalex.org/C72279823","wikidata":"https://www.wikidata.org/wiki/Q1139726","display_name":"Impulse response","level":2,"score":0.5430916547775269},{"id":"https://openalex.org/C70836080","wikidata":"https://www.wikidata.org/wiki/Q837940","display_name":"Impulse (physics)","level":2,"score":0.524692952632904},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5117999911308289},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.5039395689964294},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48576000332832336},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4373902380466461},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4131702780723572},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.39875325560569763},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27988481521606445},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09581431746482849},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.08160984516143799},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07744666934013367},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06453248858451843},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2009.4960436","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960436","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.158.6074","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.158.6074","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.nt.e-technik.uni-erlangen.de/LNT_I/publications/web/lnt2009_2.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":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W7560395","https://openalex.org/W20760429","https://openalex.org/W73693705","https://openalex.org/W2020127909","https://openalex.org/W2085151728","https://openalex.org/W2088007127","https://openalex.org/W2097491464","https://openalex.org/W2106718021","https://openalex.org/W2136821271","https://openalex.org/W2139699600","https://openalex.org/W2157515590","https://openalex.org/W2568392743","https://openalex.org/W2970850616","https://openalex.org/W4248818703","https://openalex.org/W6600294567","https://openalex.org/W6600843058","https://openalex.org/W6603089616"],"related_works":["https://openalex.org/W2987432963","https://openalex.org/W2053167664","https://openalex.org/W2780118011","https://openalex.org/W2079152323","https://openalex.org/W2128388559","https://openalex.org/W2992378684","https://openalex.org/W2964829415","https://openalex.org/W642007152","https://openalex.org/W2122233706","https://openalex.org/W2105439218"],"abstract_inverted_index":{"The":[0],"length":[1,20],"of":[2,21,41,72,86,102,108],"the":[3,8,19,22,45,65,69,73,99,121],"room":[4],"impulse":[5],"response":[6],"characterizing":[7],"acoustic":[9,70,96],"path":[10],"between":[11,64],"speaker":[12,46],"and":[13,68,80,124],"microphone":[14],"is":[15],"significantly":[16],"larger":[17],"than":[18],"analysis":[23],"window":[24],"used":[25],"for":[26,94,119],"feature":[27,56],"extraction":[28],"in":[29,106],"automatic":[30],"speech":[31,55,67],"recognition":[32,87],"(ASR)":[33],"systems.":[34],"Therefore,":[35],"reverberation":[36,103,116,122],"caused":[37],"by":[38],"multi-path":[39],"propagation":[40],"sound":[42],"waves":[43],"from":[44],"to":[47,82,114],"distant-talking":[48],"microphones":[49],"has":[50],"a":[51,62,83],"dispersive":[52,59,100],"effect":[53,60,101],"on":[54,77],"sequences.":[57],"This":[58],"causes":[61],"mismatch":[63],"input":[66],"models":[71,97],"recognizer,":[74],"usually":[75],"trained":[76],"clean":[78],"speech,":[79],"leads":[81],"significant":[84],"reduction":[85],"performance.":[88],"In":[89],"this":[90],"contribution,":[91],"different":[92],"strategies":[93],"obtaining":[95,120],"capturing":[98],"are":[104],"investigated":[105],"terms":[107],"modeling":[109],"accuracy,":[110],"flexibility":[111],"with":[112],"respect":[113],"changing":[115],"conditions,":[117],"effort":[118],"representation":[123],"decoding":[125],"complexity.":[126]},"counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}