{"id":"https://openalex.org/W1599571506","doi":"https://doi.org/10.21437/interspeech.2009-355","title":"Model based feature enhancement for automatic speech recognition in reverberant environments","display_name":"Model based feature enhancement for automatic speech recognition in reverberant environments","publication_year":2009,"publication_date":"2009-09-06","ids":{"openalex":"https://openalex.org/W1599571506","doi":"https://doi.org/10.21437/interspeech.2009-355","mag":"1599571506"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2009-355","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-355","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-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/A5110001022","display_name":"Alexander Krueger","orcid":"https://orcid.org/0009-0004-5229-8264"},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Alexander Krueger","raw_affiliation_strings":["Paderborn University:"],"affiliations":[{"raw_affiliation_string":"Paderborn University:","institution_ids":["https://openalex.org/I206945453"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082075598","display_name":"Reinhold Haeb\u2010Umbach","orcid":"https://orcid.org/0000-0001-9468-7330"},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Reinhold Haeb-Umbach","raw_affiliation_strings":["Paderborn University:"],"affiliations":[{"raw_affiliation_string":"Paderborn University:","institution_ids":["https://openalex.org/I206945453"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5110001022"],"corresponding_institution_ids":["https://openalex.org/I206945453"],"apc_list":null,"apc_paid":null,"fwci":3.1722,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.9138141,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1231","last_page":"1234"},"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":0.9983000159263611,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7870850563049316},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7676939368247986},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.581108570098877},{"id":"https://openalex.org/keywords/impulse-response","display_name":"Impulse response","score":0.5369588732719421},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5342667698860168},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.48704221844673157},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.48538291454315186},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.48483550548553467},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4741494059562683},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.45747825503349304},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.4548024833202362},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.45285728573799133},{"id":"https://openalex.org/keywords/impulse","display_name":"Impulse (physics)","score":0.4514915943145752},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.44302263855934143},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43130582571029663},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42973923683166504},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40582191944122314},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1310817301273346},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08753198385238647},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.07912322878837585},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.06572338938713074}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7870850563049316},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7676939368247986},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.581108570098877},{"id":"https://openalex.org/C72279823","wikidata":"https://www.wikidata.org/wiki/Q1139726","display_name":"Impulse response","level":2,"score":0.5369588732719421},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5342667698860168},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.48704221844673157},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.48538291454315186},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.48483550548553467},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4741494059562683},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.45747825503349304},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.4548024833202362},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.45285728573799133},{"id":"https://openalex.org/C70836080","wikidata":"https://www.wikidata.org/wiki/Q837940","display_name":"Impulse (physics)","level":2,"score":0.4514915943145752},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.44302263855934143},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43130582571029663},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42973923683166504},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40582191944122314},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1310817301273346},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08753198385238647},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.07912322878837585},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.06572338938713074},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/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},{"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:10.21437/interspeech.2009-355","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-355","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W38568696","https://openalex.org/W1512562331","https://openalex.org/W2009106392","https://openalex.org/W2033570251","https://openalex.org/W2058751961","https://openalex.org/W2125471631","https://openalex.org/W2131968171","https://openalex.org/W2137248633","https://openalex.org/W2151125621","https://openalex.org/W2158273884","https://openalex.org/W2238582461","https://openalex.org/W2970850616"],"related_works":["https://openalex.org/W3211091508","https://openalex.org/W1976952689","https://openalex.org/W2070982348","https://openalex.org/W1984921740","https://openalex.org/W2496295964","https://openalex.org/W1572861854","https://openalex.org/W2539491809","https://openalex.org/W2336887028","https://openalex.org/W2020464095","https://openalex.org/W823775484"],"abstract_inverted_index":{"In":[0,71],"this":[1],"paper":[2],"we":[3],"present":[4],"a":[5,49],"new":[6],"feature":[7],"space":[8],"dereverberation":[9],"technique":[10,64],"for":[11,19,48],"automatic":[12],"speech":[13,25,35,52],"recognition.":[14],"We":[15],"derive":[16],"an":[17],"expression":[18],"the":[20,23,28,33,38,61,68,80,90],"dependence":[21],"of":[22,60,82,92],"reverberant":[24],"features":[26,36],"in":[27],"log-mel":[29],"spectral":[30],"domain":[31],"on":[32,55,67],"non-reverberant":[34],"and":[37],"room":[39],"impulse":[40],"response.":[41],"The":[42,58],"obtained":[43],"observation":[44],"model":[45,50],"is":[46,65,85],"used":[47],"based":[51,54],"enhancement":[53,63],"Kalman":[56],"filtering.":[57],"performance":[59],"proposed":[62],"studied":[66],"AURORA5":[69],"database.":[70],"our":[72],"currently":[73],"best":[74],"configuration,":[75],"which":[76],"includes":[77],"uncertainty":[78],"decoding,":[79],"number":[81],"recognition":[83,91],"errors":[84],"approximately":[86],"halved":[87],"compared":[88],"to":[89],"unprocessed":[93],"speech.":[94]},"counts_by_year":[{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}