{"id":"https://openalex.org/W2405014675","doi":"https://doi.org/10.21437/interspeech.2014-238","title":"Room localization for distant speech recognition","display_name":"Room localization for distant speech recognition","publication_year":2014,"publication_date":"2014-09-14","ids":{"openalex":"https://openalex.org/W2405014675","doi":"https://doi.org/10.21437/interspeech.2014-238","mag":"2405014675"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2014-238","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-238","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","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/A5068044087","display_name":"Juan A. Morales-Cordovilla","orcid":"https://orcid.org/0000-0001-5411-5952"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Juan A. Morales-Cordovilla","raw_affiliation_strings":["Signal Processing and Speech Communication Laboratory, Graz University of Technology, Austria"],"affiliations":[{"raw_affiliation_string":"Signal Processing and Speech Communication Laboratory, Graz University of Technology, Austria","institution_ids":["https://openalex.org/I4092182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028295116","display_name":"Hannes Pessentheiner","orcid":"https://orcid.org/0000-0002-6930-0779"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Hannes Pessentheiner","raw_affiliation_strings":["Signal Processing and Speech Communication Laboratory, Graz University of Technology, Austria"],"affiliations":[{"raw_affiliation_string":"Signal Processing and Speech Communication Laboratory, Graz University of Technology, Austria","institution_ids":["https://openalex.org/I4092182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077678869","display_name":"Mart\u00edn Hagm\u00fcller","orcid":"https://orcid.org/0000-0002-2756-9892"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Martin Hagm\u00fcller","raw_affiliation_strings":["Signal Processing and Speech Communication Laboratory, Graz University of Technology, Austria"],"affiliations":[{"raw_affiliation_string":"Signal Processing and Speech Communication Laboratory, Graz University of Technology, Austria","institution_ids":["https://openalex.org/I4092182"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071861893","display_name":"Gernot Kubin","orcid":"https://orcid.org/0000-0002-8420-6051"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Gernot Kubin","raw_affiliation_strings":["Signal Processing and Speech Communication Laboratory, Graz University of Technology, Austria"],"affiliations":[{"raw_affiliation_string":"Signal Processing and Speech Communication Laboratory, Graz University of Technology, Austria","institution_ids":["https://openalex.org/I4092182"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5068044087"],"corresponding_institution_ids":["https://openalex.org/I4092182"],"apc_list":null,"apc_paid":null,"fwci":1.4712,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.83944353,"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":"2450","last_page":"2453"},"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9966999888420105,"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/microphone","display_name":"Microphone","score":0.7310508489608765},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7256165742874146},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7131215333938599},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.7118669152259827},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6871551871299744},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6504991054534912},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5240688323974609},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.4998021125793457},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4823271930217743},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.46037325263023376},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.44885560870170593},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08059987425804138}],"concepts":[{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.7310508489608765},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7256165742874146},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7131215333938599},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.7118669152259827},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6871551871299744},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6504991054534912},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5240688323974609},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.4998021125793457},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4823271930217743},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.46037325263023376},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.44885560870170593},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08059987425804138},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2014-238","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-238","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.714.1410","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.714.1410","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.spsc.tugraz.at/sites/default/files/Morales14_RoomLoc.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W35070573","https://openalex.org/W1579871682","https://openalex.org/W1985242443","https://openalex.org/W1989314204","https://openalex.org/W2041186534","https://openalex.org/W2147756771","https://openalex.org/W2148577181","https://openalex.org/W2229487294","https://openalex.org/W2242625287","https://openalex.org/W2251255183","https://openalex.org/W2401439450","https://openalex.org/W2408420584","https://openalex.org/W2973041694"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3177678247","https://openalex.org/W3103844505","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W2386242059"],"abstract_inverted_index":{"The":[0],"problem":[1],"of":[2,32,42,44,87,105,123],"room":[3,55,83,136],"localization":[4],"is":[5,15,119],"to":[6,79,102],"determine":[7],"where,":[8],"in":[9,85,121],"a":[10,13,17,30,37,94],"multi-room":[11],"environment,":[12],"person":[14],"producing":[16],"speech":[18,97,131],"ut-terance.":[19],"In":[20,77],"our":[21],"work,":[22],"we":[23],"are":[24],"exploiting":[25],"the":[26,40,45,81,108,117],"information":[27],"gained":[28],"from":[29],"network":[31],"microphones":[33],"installed":[34],"all":[35],"over":[36],"house,":[38],"where":[39],"lack":[41],"calibration":[43],"microphone":[46,133],"energies":[47],"creates":[48],"an":[49],"ad-ditional":[50],"challenge.":[51],"This":[52],"paper":[53,91],"compares":[54],"localizers":[56,84],"based":[57],"on":[58],"different":[59,109],"features":[60],"(such":[61,70],"as":[62,71],"energy":[63],"and":[64,68,74,125,143],"cross-correlation":[65],"be-tween":[66],"microphones)":[67],"classifiers":[69],"neural":[72],"networks":[73],"discriminative":[75],"analysis).":[76],"order":[78],"evaluate":[80],"differ-ent":[82],"terms":[86,122],"word":[88],"accuracy":[89],"this":[90],"also":[92],"presents":[93],"complete":[95],"distant":[96],"recognition":[98],"system":[99,118],"which":[100],"tries":[101],"take":[103],"advantage":[104],"synergy":[106],"between":[107],"compo-nents":[110],"without":[111],"using":[112],"any":[113],"oracle":[114],"information.":[115],"Finally,":[116],"analyzed":[120],"computational":[124],"time":[126],"resources.":[127],"Index":[128],"Terms:":[129],"Distant":[130],"recognition;":[132],"net-work;":[134],"VAD;":[135],"localization;":[137],"machine":[138],"learning":[139],"classification;":[140],"enhancement;":[141],"reverberant":[142],"noisy":[144],"environment.":[145],"1.":[146]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
