{"id":"https://openalex.org/W1993411870","doi":"https://doi.org/10.1109/icassp.2013.6639026","title":"Robustness to speaker position in distant-talking automatic speech recognition","display_name":"Robustness to speaker position in distant-talking automatic speech recognition","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W1993411870","doi":"https://doi.org/10.1109/icassp.2013.6639026","mag":"1993411870"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639026","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639026","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 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/A5052470310","display_name":"Randy G\u00f3mez","orcid":"https://orcid.org/0000-0002-3191-6818"},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Randy Gomez","raw_affiliation_strings":["Honda Research Institute Japan Company Limited, Japan","Honda Research Institute Japan, Co. Ltd., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan Company Limited, Japan","institution_ids":["https://openalex.org/I1283473643"]},{"raw_affiliation_string":"Honda Research Institute Japan, Co. Ltd., Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049329632","display_name":"Keisuke Nakamura","orcid":"https://orcid.org/0000-0002-4979-2083"},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keisuke Nakamura","raw_affiliation_strings":["Honda Research Institute Japan Company Limited, Japan","Honda Research Institute Japan, Co. Ltd., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan Company Limited, Japan","institution_ids":["https://openalex.org/I1283473643"]},{"raw_affiliation_string":"Honda Research Institute Japan, Co. Ltd., Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091708408","display_name":"Kazuhiro Nakadai","orcid":"https://orcid.org/0000-0002-6134-4558"},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuhiro Nakadai","raw_affiliation_strings":["Honda Research Institute Japan Company Limited, Japan","Honda Research Institute Japan, Co. Ltd., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan Company Limited, Japan","institution_ids":["https://openalex.org/I1283473643"]},{"raw_affiliation_string":"Honda Research Institute Japan, Co. Ltd., Japan","institution_ids":["https://openalex.org/I1283473643"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1283473643"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7034","last_page":"7038"},"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":0.9997000098228455,"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":0.9972000122070312,"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":0.7978556752204895},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7807624340057373},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7157871127128601},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.682774543762207},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.43562155961990356},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.4241224527359009},{"id":"https://openalex.org/keywords/transfer-function","display_name":"Transfer function","score":0.41047054529190063},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.17053630948066711},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09438586235046387}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7978556752204895},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7807624340057373},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7157871127128601},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.682774543762207},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.43562155961990356},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.4241224527359009},{"id":"https://openalex.org/C81299745","wikidata":"https://www.wikidata.org/wiki/Q334269","display_name":"Transfer function","level":2,"score":0.41047054529190063},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.17053630948066711},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09438586235046387},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2013.6639026","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639026","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5899999737739563,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W126265399","https://openalex.org/W1512562331","https://openalex.org/W2009106392","https://openalex.org/W2102072896","https://openalex.org/W2106259503","https://openalex.org/W2121788372","https://openalex.org/W2128653836","https://openalex.org/W2136197758","https://openalex.org/W2141418660","https://openalex.org/W2146871184","https://openalex.org/W2911394281","https://openalex.org/W2970850616","https://openalex.org/W3143675102","https://openalex.org/W4230562743","https://openalex.org/W6680064849","https://openalex.org/W6758139422"],"related_works":["https://openalex.org/W2180954594","https://openalex.org/W2052835778","https://openalex.org/W2049003611","https://openalex.org/W2127804977","https://openalex.org/W2108418243","https://openalex.org/W164103134","https://openalex.org/W2787352659","https://openalex.org/W1970611213","https://openalex.org/W4206560911","https://openalex.org/W4372260270"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,32,74],"show":[4,147],"a":[5,56,76,107],"method":[6,18,111,134,151],"that":[7,148],"significantly":[8,122],"improved":[9],"our":[10,133,162],"previous":[11],"work":[12],"in":[13,24,27,60,95,156,171],"single-channel":[14],"dereverberation.":[15],"The":[16,116],"proposed":[17,110,150],"is":[19,71,99,168],"more":[20],"robust":[21],"to":[22,44,67],"changes":[23],"speaker":[25,47,90],"position":[26,59],"distant":[28],"talking":[29],"ASR.":[30],"First,":[31],"update":[33,80,166],"the":[34,45,61,68,83,88,93,97,109,124,143,149,153],"room":[35],"transfer":[36],"function":[37,57],"(RTF)":[38],"and":[39,101,128],"weighting":[40],"parameters":[41],"for":[42],"dereverberation":[43],"target":[46,89],"position.":[48,91],"This":[49],"scheme":[50,94,167],"corrects":[51],"speech":[52,84],"power":[53,85],"variation":[54],"as":[55],"of":[58,82,87,118,158,173],"waveform":[62],"level.":[63],"Consequently,":[64],"its":[65],"impact":[66],"acoustic":[69,78,164],"model":[70,79,98,104,165,178],"verified.":[72],"Then,":[73],"implement":[75],"fast":[77,163],"reflective":[81],"level":[86],"Furthermore,":[92],"updating":[96],"simple":[100],"precludes":[102],"time-consuming":[103,177],"re-estimation.":[105,179],"As":[106],"result,":[108],"can":[112],"be":[113],"executed":[114],"online.":[115],"synergy":[117],"these":[119],"corrective":[120],"measures":[121],"minimizes":[123],"mismatch":[125],"between":[126],"training":[127],"testing":[129],"conditions.":[130],"We":[131],"test":[132],"using":[135],"real":[136],"reverberant":[137],"data":[138],"with":[139],"different":[140],"locations":[141],"inside":[142],"room.":[144],"Experimental":[145],"results":[146],"outperforms":[152],"conventional":[154],"methods":[155],"terms":[157,172],"ASR":[159],"performance.":[160],"Moreover,":[161],"at":[169],"par":[170],"recognition":[174],"performance":[175],"against":[176]},"counts_by_year":[{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}