{"id":"https://openalex.org/W1973669708","doi":"https://doi.org/10.1109/msp.2012.2205029","title":"Making Machines Understand Us in Reverberant Rooms: Robustness Against Reverberation for Automatic Speech Recognition","display_name":"Making Machines Understand Us in Reverberant Rooms: Robustness Against Reverberation for Automatic Speech Recognition","publication_year":2012,"publication_date":"2012-10-19","ids":{"openalex":"https://openalex.org/W1973669708","doi":"https://doi.org/10.1109/msp.2012.2205029","mag":"1973669708"},"language":"en","primary_location":{"id":"doi:10.1109/msp.2012.2205029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msp.2012.2205029","pdf_url":null,"source":{"id":"https://openalex.org/S120977877","display_name":"IEEE Signal Processing Magazine","issn_l":"1053-5888","issn":["1053-5888","1558-0792"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Magazine","raw_type":"journal-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/A5101618071","display_name":"Takuya Yoshioka","orcid":"https://orcid.org/0009-0003-7791-3545"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuya Yoshioka","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","[NTT Communication Science Laboratories, Kyoto, Japan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"[NTT Communication Science Laboratories, Kyoto, Japan]","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","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":["University of Erlangen-Nuremberg, Germany","[Multimedia Commun. & Signal Process., Univ. of Erlangen-Nuremberg, Erlangen, Germany]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Erlangen-Nuremberg, Germany","institution_ids":["https://openalex.org/I181369854"]},{"raw_affiliation_string":"[Multimedia Commun. & Signal Process., Univ. of Erlangen-Nuremberg, Erlangen, Germany]","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Marc Delcroix","raw_affiliation_strings":["NTT Communication Science Laboratories, Kyoto, Japan","[NTT Communication Science Laboratories, Kyoto, Japan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"[NTT Communication Science Laboratories, Kyoto, Japan]","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069398831","display_name":"Keisuke Kinoshita","orcid":"https://orcid.org/0009-0008-7987-8188"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keisuke Kinoshita","raw_affiliation_strings":["NTT Communication Science Laboratories, Japan","[NTT Communication Science Laboratories, Kyoto, Japan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"[NTT Communication Science Laboratories, Kyoto, Japan]","institution_ids":["https://openalex.org/I2251713219"]}]},{"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":["Audio Research Laboratory, Chair of Multimedia Communications and Signal Processing, University of Erlangen-Nuremberg, Germany","[Multimedia Commun. & Signal Process., Univ. of Erlangen-Nuremberg, Erlangen, Germany]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio Research Laboratory, Chair of Multimedia Communications and Signal Processing, University of Erlangen-Nuremberg, Germany","institution_ids":["https://openalex.org/I181369854"]},{"raw_affiliation_string":"[Multimedia Commun. & Signal Process., Univ. of Erlangen-Nuremberg, Erlangen, Germany]","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Nakatani","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Japan","[NTT Communication Science Laboratories, Kyoto, Japan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"[NTT Communication Science Laboratories, Kyoto, Japan]","institution_ids":["https://openalex.org/I2251713219"]}]},{"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":["University of Erlangen-Nuremberg, Germany","[Multimedia Commun. & Signal Process., Univ. of Erlangen-Nuremberg, Erlangen, Germany]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Erlangen-Nuremberg, Germany","institution_ids":["https://openalex.org/I181369854"]},{"raw_affiliation_string":"[Multimedia Commun. & Signal Process., Univ. of Erlangen-Nuremberg, Erlangen, Germany]","institution_ids":["https://openalex.org/I181369854"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":18.5197,"has_fulltext":false,"cited_by_count":232,"citation_normalized_percentile":{"value":0.9958707,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"29","issue":"6","first_page":"114","last_page":"126"},"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":0.9994000196456909,"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":0.9987000226974487,"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/computer-science","display_name":"Computer science","score":0.8220363855361938},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6985690593719482},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6337972283363342},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.6134299039840698},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5520383715629578},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.5201205015182495},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5038260817527771},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4772196412086487},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.45584553480148315},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.4554145336151123},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.4526694416999817},{"id":"https://openalex.org/keywords/speech-analytics","display_name":"Speech analytics","score":0.42976707220077515},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3276830017566681},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23410198092460632},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.18679794669151306},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.131361722946167},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12877744436264038},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.09253567457199097}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8220363855361938},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6985690593719482},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6337972283363342},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.6134299039840698},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5520383715629578},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.5201205015182495},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5038260817527771},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4772196412086487},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.45584553480148315},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.4554145336151123},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.4526694416999817},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.42976707220077515},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3276830017566681},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23410198092460632},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.18679794669151306},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.131361722946167},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12877744436264038},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.09253567457199097},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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":1,"locations":[{"id":"doi:10.1109/msp.2012.2205029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msp.2012.2205029","pdf_url":null,"source":{"id":"https://openalex.org/S120977877","display_name":"IEEE Signal Processing Magazine","issn_l":"1053-5888","issn":["1053-5888","1558-0792"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Magazine","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W76514835","https://openalex.org/W87496662","https://openalex.org/W151751907","https://openalex.org/W214395912","https://openalex.org/W1230632900","https://openalex.org/W1512562331","https://openalex.org/W1522463960","https://openalex.org/W1573570773","https://openalex.org/W1578856370","https://openalex.org/W1992272902","https://openalex.org/W1994396704","https://openalex.org/W2005733316","https://openalex.org/W2006783645","https://openalex.org/W2009106392","https://openalex.org/W2014768838","https://openalex.org/W2045036776","https://openalex.org/W2045043668","https://openalex.org/W2085151728","https://openalex.org/W2100969003","https://openalex.org/W2104780554","https://openalex.org/W2106554350","https://openalex.org/W2106718021","https://openalex.org/W2107992675","https://openalex.org/W2108327698","https://openalex.org/W2110606453","https://openalex.org/W2117518720","https://openalex.org/W2117678320","https://openalex.org/W2118479009","https://openalex.org/W2123765505","https://openalex.org/W2125610823","https://openalex.org/W2130283666","https://openalex.org/W2130361043","https://openalex.org/W2131118158","https://openalex.org/W2132054610","https://openalex.org/W2137075158","https://openalex.org/W2140866802","https://openalex.org/W2142352807","https://openalex.org/W2145475542","https://openalex.org/W2146083413","https://openalex.org/W2146871184","https://openalex.org/W2148898720","https://openalex.org/W2157019774","https://openalex.org/W2164502538","https://openalex.org/W2188162373","https://openalex.org/W4206633762","https://openalex.org/W4256112632","https://openalex.org/W4296927107","https://openalex.org/W6608656091","https://openalex.org/W6628167197","https://openalex.org/W6630574771","https://openalex.org/W6634340323","https://openalex.org/W6679607613","https://openalex.org/W6683228439","https://openalex.org/W6686978693"],"related_works":["https://openalex.org/W134179020","https://openalex.org/W2184127972","https://openalex.org/W2134473597","https://openalex.org/W642007152","https://openalex.org/W2909367404","https://openalex.org/W2525874696","https://openalex.org/W2008120082","https://openalex.org/W1965739709","https://openalex.org/W2218471654","https://openalex.org/W4241475234"],"abstract_inverted_index":{"Speech":[0],"recognition":[1,134,154],"technology":[2,135],"has":[3],"left":[4],"the":[5,47,71,74,140,149],"research":[6],"laboratory":[7],"and":[8,21,35,99],"is":[9,136],"increasingly":[10],"coming":[11],"into":[12],"practical":[13],"use,":[14],"enabling":[15],"a":[16,43,116,126],"wide":[17],"spectrum":[18],"of":[19,31,38,52,76,92,118,142,151],"innovative":[20],"exciting":[22],"voice-driven":[23],"applications":[24,40,54,84],"that":[25,130],"are":[26,63,125],"radically":[27],"changing":[28],"our":[29],"way":[30],"accessing":[32],"digital":[33],"services":[34],"information.":[36],"Most":[37],"today's":[39],"still":[41],"require":[42],"microphone":[44],"located":[45],"near":[46],"talker.":[48],"However,":[49],"almost":[50],"all":[51],"these":[53],"would":[55],"benefit":[56,110],"from":[57,70,111],"distant-talking":[58,112],"speech":[59,88,133,143,153],"capturing,":[60],"where":[61],"talkers":[62],"able":[64],"to":[65],"speak":[66],"at":[67],"some":[68],"distance":[69],"microphones":[72,124],"without":[73],"encumbrance":[75],"handheld":[77],"or":[78],"body-worn":[79],"equipment":[80],"[1].":[81],"For":[82],"example,":[83],"such":[85],"as":[86,145,147],"meeting":[87],"recognition,":[89],"automatic":[90],"annotation":[91],"consumer-generated":[93],"videos,":[94],"speech-to-speech":[95],"translation":[96],"in":[97],"teleconferencing,":[98],"hands-free":[100],"interfaces":[101],"for":[102,115,138],"controlling":[103],"consumer-products,":[104],"like":[105],"interactive":[106],"TV,":[107],"will":[108],"greatly":[109],"operation.":[113],"Furthermore,":[114],"number":[117],"unexplored":[119],"but":[120],"important":[121],"applications,":[122],"distant":[123,131],"prerequisite.":[127],"This":[128],"means":[129],"talking":[132],"essential":[137],"extending":[139],"availability":[141],"recognizers":[144],"well":[146],"enhancing":[148],"convenience":[150],"existing":[152],"applications.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":19},{"year":2018,"cited_by_count":23},{"year":2017,"cited_by_count":25},{"year":2016,"cited_by_count":20},{"year":2015,"cited_by_count":30},{"year":2014,"cited_by_count":31},{"year":2013,"cited_by_count":13},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
