{"id":"https://openalex.org/W246278971","doi":"https://doi.org/10.21437/interspeech.2008-206","title":"Robust front end processing for speech recognition in reverberant environments: utilization of speech characteristics","display_name":"Robust front end processing for speech recognition in reverberant environments: utilization of speech characteristics","publication_year":2008,"publication_date":"2008-09-22","ids":{"openalex":"https://openalex.org/W246278971","doi":"https://doi.org/10.21437/interspeech.2008-206","mag":"246278971"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2008-206","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-206","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2008","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/A5082636388","display_name":"Rico Petrick","orcid":null},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"TU Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Rico Petrick","raw_affiliation_strings":["TU Dresden, Dresden, Germany"],"affiliations":[{"raw_affiliation_string":"TU Dresden, Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034792613","display_name":"Xugang Lu","orcid":"https://orcid.org/0000-0001-7075-448X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xugang Lu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014199725","display_name":"Masashi Unoki","orcid":"https://orcid.org/0000-0002-6605-2052"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masashi Unoki","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055059119","display_name":"Masato Akagi","orcid":"https://orcid.org/0000-0003-2450-6754"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masato Akagi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5103817232","display_name":"R\u00fcdiger Hoffmann","orcid":null},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"TU Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"R\u00fcdiger Hoffmann","raw_affiliation_strings":["TU Dresden, Dresden, Germany"],"affiliations":[{"raw_affiliation_string":"TU Dresden, Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5082636388"],"corresponding_institution_ids":["https://openalex.org/I78650965"],"apc_list":null,"apc_paid":null,"fwci":0.7597,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.69322476,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"658","last_page":"661"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9840999841690063,"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":0.9840999841690063,"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":0.9139000177383423,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7196265459060669},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7194948792457581},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.6138601899147034},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.5937468409538269},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.46565893292427063}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7196265459060669},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7194948792457581},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.6138601899147034},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.5937468409538269},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.46565893292427063},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2008-206","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-206","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2008","raw_type":"proceedings-article"},{"id":"pmh:oai:dspace.jaist.ac.jp:10119/9985","is_oa":false,"landing_page_url":"http://hdl.handle.net/10119/9985","pdf_url":null,"source":{"id":"https://openalex.org/S4406922663","display_name":"JAIST Repository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3135230428","https://openalex.org/W2904739811","https://openalex.org/W249088392","https://openalex.org/W2152158029","https://openalex.org/W2012540220","https://openalex.org/W2559837139","https://openalex.org/W2131711534","https://openalex.org/W2559040841","https://openalex.org/W284174822","https://openalex.org/W114661351"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"two":[3],"methods":[4,16,32,94,128,144],"for":[5,124,148],"robust":[6],"automatic":[7],"speech":[8],"recognition":[9,97],"(ASR)":[10],"in":[11,100,131,140,157,175],"reverberant":[12,125,134,149],"environments.":[13],"Unlike":[14],"other":[15],"which":[17,59,88,170],"mostly":[18],"apply":[19],"inverse":[20],"filtering":[21],"by":[22],"blindly":[23],"estimated":[24],"room":[25],"impulse":[26],"responses":[27],"to":[28,62,114],"achieve":[29],"dereverberation,":[30],"theproposed":[31],"are":[33,60,129],"based":[34,48],"on":[35,159],"the":[36,39,55,76,83,96,127,160,166],"utilization":[37],"of":[38,41,54,80,106,117],"characteristics":[40],"speech.":[42],"The":[43,65],"first":[44],"method":[45,67],"-":[46,68],"Harmonicity":[47],"Feature":[49,72],"Analysis":[50,73],"\u2013":[51,74],"takes":[52],"advantage":[53],"harmonic":[56],"componentsof":[57],"speech,":[58,81],"assumed":[61],"be":[63],"undistorted.":[64],"second":[66],"Temporal":[69],"Power":[70],"Envelope":[71],"utilizes":[75],"temporal":[77,86,122],"modulation":[78,121],"structure":[79,123],"representing":[82],"phoneme":[84],"level":[85],"events":[87],"contain":[89],"most":[90],"intelligibility":[91],"information.":[92],"Both":[93],"increase":[95],"performance":[98,156,164],"remarkably":[99],"a":[101],"different":[102],"way.":[103],"Combining":[104],"both":[105,143],"them":[107],"connects":[108],"their":[109,155,163],"individual":[110],"advantages.":[111],"In":[112,151],"order":[113],"examine":[115],"theperformance":[116],"utilizing":[118],"harmonicity":[119],"and":[120,133],"ASR,":[126],"tested":[130],"clean":[132],"training.":[135,150],"As":[136],"results":[137],"show,":[138],"even":[139],"strong":[141],"reverberantconditions":[142],"obtain":[145],"practical":[146],"applicableperformance":[147],"addition,":[152],"besides":[153],"testing":[154],"dependency":[158],"reverberation":[161],"time,":[162],"considering":[165],"speaker-to-microphone":[167],"distanceis":[168],"tested,":[169],"is":[171],"another":[172],"new":[173],"contributions":[174],"this":[176],"paper.":[177]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
