{"id":"https://openalex.org/W3135282443","doi":"https://doi.org/10.1145/3442629","title":"Automatic Speech Recognition for Indoor HRI Scenarios","display_name":"Automatic Speech Recognition for Indoor HRI Scenarios","publication_year":2021,"publication_date":"2021-03-08","ids":{"openalex":"https://openalex.org/W3135282443","doi":"https://doi.org/10.1145/3442629","mag":"3135282443"},"language":"en","primary_location":{"id":"doi:10.1145/3442629","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3442629","pdf_url":null,"source":{"id":"https://openalex.org/S4210193251","display_name":"ACM Transactions on Human-Robot Interaction","issn_l":"2573-9522","issn":["2573-9522"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Human-Robot Interaction","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/A5103827948","display_name":"Jos\u00e9 N\u00f3voa","orcid":null},"institutions":[{"id":"https://openalex.org/I69737025","display_name":"University of Chile","ror":"https://ror.org/047gc3g35","country_code":"CL","type":"education","lineage":["https://openalex.org/I69737025"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 Novoa","raw_affiliation_strings":["Speech Processing and Transmission Laboratory, University of Chile, Santiago, Chile"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Processing and Transmission Laboratory, University of Chile, Santiago, Chile","institution_ids":["https://openalex.org/I69737025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007921391","display_name":"Rodrigo Mah\u00fa","orcid":"https://orcid.org/0000-0002-6374-8003"},"institutions":[{"id":"https://openalex.org/I69737025","display_name":"University of Chile","ror":"https://ror.org/047gc3g35","country_code":"CL","type":"education","lineage":["https://openalex.org/I69737025"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"Rodrigo Mahu","raw_affiliation_strings":["Speech Processing and Transmission Laboratory, University of Chile, Santiago, Chile"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Processing and Transmission Laboratory, University of Chile, Santiago, Chile","institution_ids":["https://openalex.org/I69737025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055118748","display_name":"Jorge Wuth","orcid":null},"institutions":[{"id":"https://openalex.org/I69737025","display_name":"University of Chile","ror":"https://ror.org/047gc3g35","country_code":"CL","type":"education","lineage":["https://openalex.org/I69737025"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"Jorge Wuth","raw_affiliation_strings":["Speech Processing and Transmission Laboratory, University of Chile, Santiago, Chile"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Processing and Transmission Laboratory, University of Chile, Santiago, Chile","institution_ids":["https://openalex.org/I69737025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103769815","display_name":"Juan Pablo Escudero","orcid":"https://orcid.org/0000-0002-7613-027X"},"institutions":[{"id":"https://openalex.org/I69737025","display_name":"University of Chile","ror":"https://ror.org/047gc3g35","country_code":"CL","type":"education","lineage":["https://openalex.org/I69737025"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"Juan Pablo Escudero","raw_affiliation_strings":["Speech Processing and Transmission Laboratory, University of Chile, Santiago, Chile"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Processing and Transmission Laboratory, University of Chile, Santiago, Chile","institution_ids":["https://openalex.org/I69737025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013929728","display_name":"Josu\u00e9 Fredes","orcid":"https://orcid.org/0000-0002-9614-4193"},"institutions":[{"id":"https://openalex.org/I69737025","display_name":"University of Chile","ror":"https://ror.org/047gc3g35","country_code":"CL","type":"education","lineage":["https://openalex.org/I69737025"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"Josu\u00e9 Fredes","raw_affiliation_strings":["Speech Processing and Transmission Laboratory, University of Chile, Santiago, Chile"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Processing and Transmission Laboratory, University of Chile, Santiago, Chile","institution_ids":["https://openalex.org/I69737025"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029824436","display_name":"N\u00e9stor Becerra Yoma","orcid":"https://orcid.org/0000-0002-3052-4687"},"institutions":[{"id":"https://openalex.org/I69737025","display_name":"University of Chile","ror":"https://ror.org/047gc3g35","country_code":"CL","type":"education","lineage":["https://openalex.org/I69737025"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"N\u00e9stor Becerra Yoma","raw_affiliation_strings":["Speech Processing and Transmission Laboratory, University of Chile, Santiago, Chile"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Processing and Transmission Laboratory, University of Chile, Santiago, Chile","institution_ids":["https://openalex.org/I69737025"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5393,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.85670877,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"10","issue":"2","first_page":"1","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9962000250816345,"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":0.7573864459991455},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.661676287651062},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.6075765490531921},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.4760739207267761},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.46399232745170593},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.4542132616043091},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.45158275961875916},{"id":"https://openalex.org/keywords/upload","display_name":"Upload","score":0.43211114406585693},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34906649589538574},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11069393157958984},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10999414324760437}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7573864459991455},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.661676287651062},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.6075765490531921},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.4760739207267761},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.46399232745170593},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.4542132616043091},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.45158275961875916},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.43211114406585693},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34906649589538574},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11069393157958984},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10999414324760437},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/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},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3442629","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3442629","pdf_url":null,"source":{"id":"https://openalex.org/S4210193251","display_name":"ACM Transactions on Human-Robot Interaction","issn_l":"2573-9522","issn":["2573-9522"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Human-Robot Interaction","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G7912527284","display_name":null,"funder_award_id":"62909-17-1-2002","funder_id":"https://openalex.org/F4320338298","funder_display_name":"Office of Naval Research Global"}],"funders":[{"id":"https://openalex.org/F4320338298","display_name":"Office of Naval Research Global","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":77,"referenced_works":["https://openalex.org/W81726370","https://openalex.org/W187434241","https://openalex.org/W619584837","https://openalex.org/W1496342644","https://openalex.org/W1498991127","https://openalex.org/W1517606245","https://openalex.org/W1563168000","https://openalex.org/W1581253957","https://openalex.org/W1602122992","https://openalex.org/W1909727437","https://openalex.org/W1931312565","https://openalex.org/W1968531668","https://openalex.org/W1989271290","https://openalex.org/W1994396704","https://openalex.org/W1995562189","https://openalex.org/W2007223396","https://openalex.org/W2034587361","https://openalex.org/W2038118634","https://openalex.org/W2038891231","https://openalex.org/W2056489736","https://openalex.org/W2062164080","https://openalex.org/W2063703533","https://openalex.org/W2064675550","https://openalex.org/W2072933891","https://openalex.org/W2077541282","https://openalex.org/W2078958793","https://openalex.org/W2099739380","https://openalex.org/W2112632589","https://openalex.org/W2129578073","https://openalex.org/W2131342762","https://openalex.org/W2138780138","https://openalex.org/W2143612262","https://openalex.org/W2148613904","https://openalex.org/W2158791054","https://openalex.org/W2160145433","https://openalex.org/W2160815625","https://openalex.org/W2220867547","https://openalex.org/W2251372956","https://openalex.org/W2255129608","https://openalex.org/W2291522532","https://openalex.org/W2398058106","https://openalex.org/W2399093011","https://openalex.org/W2407778575","https://openalex.org/W2412588858","https://openalex.org/W2515753980","https://openalex.org/W2515863432","https://openalex.org/W2517914016","https://openalex.org/W2519224033","https://openalex.org/W2524849597","https://openalex.org/W2556673367","https://openalex.org/W2561675875","https://openalex.org/W2567032617","https://openalex.org/W2583851971","https://openalex.org/W2589530322","https://openalex.org/W2591355762","https://openalex.org/W2591917595","https://openalex.org/W2593216051","https://openalex.org/W2597001495","https://openalex.org/W2600336481","https://openalex.org/W2603415636","https://openalex.org/W2622203030","https://openalex.org/W2772028198","https://openalex.org/W2784252582","https://openalex.org/W2810084418","https://openalex.org/W2913210897","https://openalex.org/W2963244312","https://openalex.org/W3023745411","https://openalex.org/W3105118415","https://openalex.org/W3141239769","https://openalex.org/W4205559380","https://openalex.org/W4233686892","https://openalex.org/W4236925753","https://openalex.org/W4237536504","https://openalex.org/W4244495895","https://openalex.org/W4246535998","https://openalex.org/W4251397122","https://openalex.org/W4376562541"],"related_works":["https://openalex.org/W1656519308","https://openalex.org/W2042717753","https://openalex.org/W2022849831","https://openalex.org/W2037265366","https://openalex.org/W2944823289","https://openalex.org/W2026603686","https://openalex.org/W2331622705","https://openalex.org/W1562475690","https://openalex.org/W1488529827","https://openalex.org/W876328409"],"abstract_inverted_index":{"This":[0],"article":[1],"presents":[2],"a":[3,69],"stand-alone":[4],"automatic":[5,41],"speech":[6,42,90,161,181],"recognition":[7,43,162,182],"system":[8],"that":[9,170],"accounts":[10],"for":[11,23,111,120],"listener":[12],"movement,":[13],"time-varying":[14,79],"reverberation":[15],"effects,":[16],"environmental":[17,85],"noise,":[18],"and":[19,56,58,83,99,136,175,189],"user":[20],"position":[21],"information":[22],"beamforming":[24],"approaches":[25],"in":[26,45],"an":[27,165],"HRI":[28,46,131,157],"setting.":[29],"We":[30],"raise":[31],"the":[32,36,49,52,60,78,121,127,146,152,159,185],"importance":[33],"of":[34,40,51,59,129],"replacing":[35],"classical":[37],"black-box":[38],"integration":[39],"technology":[44],"applications":[47],"with":[48,132,184],"incorporation":[50],"acoustic":[53,80],"environment":[54],"representation":[55],"modeling,":[57],"target":[61],"source":[62,108],"direction.":[63],"Test":[64],"data":[65,135,150],"were":[66,92],"recorded":[67],"on":[68,139],"real":[70],"robot":[71],"under":[72],"various":[73],"moving":[74],"conditions.":[75],"For":[76],"addressing":[77],"channel":[81,97],"problem":[82],"incorporating":[84],"effect":[86],"during":[87],"training,":[88],"clean":[89],"samples":[91],"passed":[93],"through":[94],"estimated":[95],"static":[96],"responses":[98],"noise":[100],"was":[101],"added.":[102],"Beamforming":[103],"is":[104,118,171],"investigated":[105],"regarding":[106],"oracle":[107],"tracking":[109],"using,":[110],"instance,":[112],"image":[113],"processing.":[114],"The":[115],"proposed":[116],"strategy":[117],"interesting":[119],"robotics":[122],"community,":[123],"because":[124],"it":[125],"allows":[126],"development":[128],"voice-based":[130],"limited":[133],"training":[134],"without":[137],"relying":[138],"third-party":[140],"technologies":[141],"or":[142],"Internet":[143],"access":[144],"eliminating":[145],"need":[147],"to":[148,151],"upload":[149],"cloud.":[153],"In":[154],"our":[155],"mobile":[156],"scenario,":[158],"resulting":[160],"engine":[163],"provided":[164],"average":[166],"word":[167],"error":[168],"rate":[169],"at":[172],"least":[173],"19%":[174],"34%":[176],"lower":[177],"than":[178],"publicly":[179],"available":[180],"APIs":[183],"playback":[186],"(i.e.,":[187],"loudspeaker)":[188],"human":[190],"testing":[191],"modalities,":[192],"respectively.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}