{"id":"https://openalex.org/W4388117501","doi":"https://doi.org/10.23919/eusipco58844.2023.10290125","title":"Room Adaptation of Training Data for Distant Speech Recognition","display_name":"Room Adaptation of Training Data for Distant Speech Recognition","publication_year":2023,"publication_date":"2023-09-04","ids":{"openalex":"https://openalex.org/W4388117501","doi":"https://doi.org/10.23919/eusipco58844.2023.10290125"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco58844.2023.10290125","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/eusipco58844.2023.10290125","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 31st European Signal Processing Conference (EUSIPCO)","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/A5078802241","display_name":"James Fosburgh","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125787","display_name":"Nuance Communications (United States)","ror":"https://ror.org/0311h6702","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Fosburgh","raw_affiliation_strings":["Nuance Communications Inc.,Research &#x0026; Development,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications Inc.,Research &#x0026; Development,USA","institution_ids":["https://openalex.org/I4210125787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108774400","display_name":"Dushyant Sharma","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125787","display_name":"Nuance Communications (United States)","ror":"https://ror.org/0311h6702","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dushyant Sharma","raw_affiliation_strings":["Nuance Communications Inc.,Research &#x0026; Development,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications Inc.,Research &#x0026; Development,USA","institution_ids":["https://openalex.org/I4210125787"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016227729","display_name":"Patrick A. Naylor","orcid":"https://orcid.org/0000-0001-8546-8013"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Patrick A. Naylor","raw_affiliation_strings":["Imperial College,Electrical &#x0026; Electronic Engineering,London,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College,Electrical &#x0026; Electronic Engineering,London,UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14231769,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"71","last_page":"75"},"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":0.9984999895095825,"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":0.998199999332428,"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":0.7766644954681396},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7730143070220947},{"id":"https://openalex.org/keywords/loudspeaker","display_name":"Loudspeaker","score":0.7276722192764282},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.7266435027122498},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.6770032644271851},{"id":"https://openalex.org/keywords/impulse-response","display_name":"Impulse response","score":0.600795567035675},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5055694580078125},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4635353088378906},{"id":"https://openalex.org/keywords/impulse","display_name":"Impulse (physics)","score":0.446418821811676},{"id":"https://openalex.org/keywords/transfer-function","display_name":"Transfer function","score":0.43997058272361755},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4303649961948395},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3539274334907532},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3281124234199524},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.22403672337532043},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1133246123790741},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09013637900352478}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7766644954681396},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7730143070220947},{"id":"https://openalex.org/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"score":0.7276722192764282},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.7266435027122498},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.6770032644271851},{"id":"https://openalex.org/C72279823","wikidata":"https://www.wikidata.org/wiki/Q1139726","display_name":"Impulse response","level":2,"score":0.600795567035675},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5055694580078125},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4635353088378906},{"id":"https://openalex.org/C70836080","wikidata":"https://www.wikidata.org/wiki/Q837940","display_name":"Impulse (physics)","level":2,"score":0.446418821811676},{"id":"https://openalex.org/C81299745","wikidata":"https://www.wikidata.org/wiki/Q334269","display_name":"Transfer function","level":2,"score":0.43997058272361755},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4303649961948395},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3539274334907532},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3281124234199524},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.22403672337532043},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1133246123790741},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09013637900352478},{"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/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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco58844.2023.10290125","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/eusipco58844.2023.10290125","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 31st European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1999542175","https://openalex.org/W2099464104","https://openalex.org/W2117678320","https://openalex.org/W2143643945","https://openalex.org/W2410879554","https://openalex.org/W2696967604","https://openalex.org/W2891997645","https://openalex.org/W2903055733","https://openalex.org/W3086154751","https://openalex.org/W3095173472","https://openalex.org/W3117722298","https://openalex.org/W3198134544","https://openalex.org/W4226279385","https://openalex.org/W4285116935","https://openalex.org/W4312979902","https://openalex.org/W6681126137","https://openalex.org/W6787857153"],"related_works":["https://openalex.org/W3199097733","https://openalex.org/W2987432963","https://openalex.org/W2053167664","https://openalex.org/W2780118011","https://openalex.org/W2114074729","https://openalex.org/W2079152323","https://openalex.org/W2128388559","https://openalex.org/W4255044973","https://openalex.org/W2499802997","https://openalex.org/W2112059504"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,27,38,42,55,60,65,92,102,118,128],"novel":[3],"signal":[4],"processing-based":[5],"approach":[6,32,115],"for":[7,12,84,101],"estimating":[8],"room":[9,39],"impulse":[10,35,68],"responses":[11,69],"augmentation":[13,114],"of":[14,37,91,95,98],"ASR":[15,86,108],"training":[16,82],"data":[17,113],"that":[18,106],"is":[19],"best":[20],"suited":[21],"to":[22,48,74,78,127],"the":[23,50,89],"reverberation":[24],"characteristics":[25],"in":[26,122],"particular":[28],"acoustic":[29],"space.":[30],"Our":[31],"estimates":[33],"an":[34,80,85,107],"response":[36],"by":[40,64],"using":[41,130],"supervised":[43],"adaptive":[44],"system":[45,129],"identification":[46],"algorithm":[47],"extract":[49],"relative":[51,120],"transfer":[52],"function":[53],"between":[54],"speech":[56,76],"source":[57],"played":[58],"through":[59],"loudspeaker":[61],"and":[62],"recorded":[63],"microphone.":[66],"These":[67],"can":[70,116],"then":[71],"be":[72],"applied":[73],"clean":[75],"files":[77],"create":[79],"augmented":[81],"set":[83],"system.":[87],"Given":[88],"availability":[90],"small":[93],"amount":[94],"this":[96],"type":[97],"playback":[99],"audio":[100],"room,":[103],"we":[104],"show":[105],"model":[109],"trained":[110],"with":[111],"our":[112],"provide":[117],"19%":[119],"reduction":[121],"word":[123],"error":[124],"rate":[125],"compared":[126],"random":[131],"augmentation.":[132]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
