{"id":"https://openalex.org/W3110753023","doi":"https://doi.org/10.1142/s0219843620500231","title":"Speech Envelope Dynamics for Noise-Robust Auditory Scene Analysis in Robotics","display_name":"Speech Envelope Dynamics for Noise-Robust Auditory Scene Analysis in Robotics","publication_year":2020,"publication_date":"2020-12-01","ids":{"openalex":"https://openalex.org/W3110753023","doi":"https://doi.org/10.1142/s0219843620500231","mag":"3110753023"},"language":"en","primary_location":{"id":"doi:10.1142/s0219843620500231","is_oa":true,"landing_page_url":"https://doi.org/10.1142/s0219843620500231","pdf_url":null,"source":{"id":"https://openalex.org/S75343556","display_name":"International Journal of Humanoid Robotics","issn_l":"0219-8436","issn":["0219-8436","1793-6942"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Humanoid Robotics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1142/s0219843620500231","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046028450","display_name":"Francesco Rea","orcid":"https://orcid.org/0000-0001-8535-223X"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Francesco Rea","raw_affiliation_strings":["Robotics Brain and Cognitive Sciences, Istituto Italiano di Tecnologia, Via Enrico Melen, 83, 16152 Genova, GE, Italy"],"raw_orcid":"https://orcid.org/0000-0001-8535-223X","affiliations":[{"raw_affiliation_string":"Robotics Brain and Cognitive Sciences, Istituto Italiano di Tecnologia, Via Enrico Melen, 83, 16152 Genova, GE, Italy","institution_ids":["https://openalex.org/I30771326"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060379266","display_name":"Austin Kothig","orcid":"https://orcid.org/0000-0003-2194-4572"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Austin Kothig","raw_affiliation_strings":["Social and Intelligent Robotics Research Lab (SIRRL), University of Waterloo, 200 University Avenue West, Waterloo, ON N2L 3G1, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Social and Intelligent Robotics Research Lab (SIRRL), University of Waterloo, 200 University Avenue West, Waterloo, ON N2L 3G1, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056776764","display_name":"Lukas Grasse","orcid":null},"institutions":[{"id":"https://openalex.org/I107949126","display_name":"University of Lethbridge","ror":"https://ror.org/044j76961","country_code":"CA","type":"education","lineage":["https://openalex.org/I107949126"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Lukas Grasse","raw_affiliation_strings":["Department of Neuroscience, University of Lethbridge, 4401 University Drive West, Lethbridge, AB T1K 3M4, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Neuroscience, University of Lethbridge, 4401 University Drive West, Lethbridge, AB T1K 3M4, Canada","institution_ids":["https://openalex.org/I107949126"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042663063","display_name":"Matthew S. Tata","orcid":null},"institutions":[{"id":"https://openalex.org/I107949126","display_name":"University of Lethbridge","ror":"https://ror.org/044j76961","country_code":"CA","type":"education","lineage":["https://openalex.org/I107949126"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Matthew Tata","raw_affiliation_strings":["Department of Neuroscience, University of Lethbridge, 4401 University Drive West, Lethbridge, AB T1K 3M4, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Neuroscience, University of Lethbridge, 4401 University Drive West, Lethbridge, AB T1K 3M4, Canada","institution_ids":["https://openalex.org/I107949126"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5046028450"],"corresponding_institution_ids":["https://openalex.org/I30771326"],"apc_list":null,"apc_paid":null,"fwci":0.1485,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.45649246,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":"17","issue":"06","first_page":"2050023","last_page":"2050023"},"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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8142118453979492},{"id":"https://openalex.org/keywords/auditory-scene-analysis","display_name":"Auditory scene analysis","score":0.8018946051597595},{"id":"https://openalex.org/keywords/binaural-recording","display_name":"Binaural recording","score":0.7484833598136902},{"id":"https://openalex.org/keywords/computational-auditory-scene-analysis","display_name":"Computational auditory scene analysis","score":0.6953899264335632},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6215032339096069},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5033738017082214},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.483518123626709},{"id":"https://openalex.org/keywords/envelope","display_name":"Envelope (radar)","score":0.48223981261253357},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.46468380093574524},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4192826747894287},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.39085474610328674},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07397177815437317},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07274132966995239}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8142118453979492},{"id":"https://openalex.org/C38129911","wikidata":"https://www.wikidata.org/wiki/Q4820038","display_name":"Auditory scene analysis","level":3,"score":0.8018946051597595},{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.7484833598136902},{"id":"https://openalex.org/C73208851","wikidata":"https://www.wikidata.org/wiki/Q5157303","display_name":"Computational auditory scene analysis","level":2,"score":0.6953899264335632},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6215032339096069},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5033738017082214},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.483518123626709},{"id":"https://openalex.org/C65155139","wikidata":"https://www.wikidata.org/wiki/Q5380912","display_name":"Envelope (radar)","level":3,"score":0.48223981261253357},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.46468380093574524},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4192826747894287},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.39085474610328674},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07397177815437317},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07274132966995239},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"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:10.1142/s0219843620500231","is_oa":true,"landing_page_url":"https://doi.org/10.1142/s0219843620500231","pdf_url":null,"source":{"id":"https://openalex.org/S75343556","display_name":"International Journal of Humanoid Robotics","issn_l":"0219-8436","issn":["0219-8436","1793-6942"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Humanoid Robotics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1142/s0219843620500231","is_oa":true,"landing_page_url":"https://doi.org/10.1142/s0219843620500231","pdf_url":null,"source":{"id":"https://openalex.org/S75343556","display_name":"International Journal of Humanoid Robotics","issn_l":"0219-8436","issn":["0219-8436","1793-6942"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Humanoid Robotics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W182689536","https://openalex.org/W1494198834","https://openalex.org/W1581848821","https://openalex.org/W1591446137","https://openalex.org/W1603215226","https://openalex.org/W1675831118","https://openalex.org/W1940727076","https://openalex.org/W1971920230","https://openalex.org/W1993287287","https://openalex.org/W2000244215","https://openalex.org/W2004088673","https://openalex.org/W2027250573","https://openalex.org/W2028184103","https://openalex.org/W2034740570","https://openalex.org/W2037684811","https://openalex.org/W2038484192","https://openalex.org/W2046317813","https://openalex.org/W2056486423","https://openalex.org/W2059440439","https://openalex.org/W2060237968","https://openalex.org/W2069432516","https://openalex.org/W2074047423","https://openalex.org/W2075562975","https://openalex.org/W2085940008","https://openalex.org/W2097191389","https://openalex.org/W2100907900","https://openalex.org/W2110525007","https://openalex.org/W2111320049","https://openalex.org/W2116933335","https://openalex.org/W2118980133","https://openalex.org/W2138164020","https://openalex.org/W2147336803","https://openalex.org/W2164356097","https://openalex.org/W2170534702","https://openalex.org/W2277299793","https://openalex.org/W2413091727","https://openalex.org/W2414268291","https://openalex.org/W2618602706","https://openalex.org/W2742299865","https://openalex.org/W2764199905","https://openalex.org/W2906978576","https://openalex.org/W2968798537","https://openalex.org/W4244521453","https://openalex.org/W4250772347"],"related_works":["https://openalex.org/W2362704157","https://openalex.org/W3199891340","https://openalex.org/W133022121","https://openalex.org/W1567098080","https://openalex.org/W2550493152","https://openalex.org/W2345846362","https://openalex.org/W1578900076","https://openalex.org/W2294106860","https://openalex.org/W2517450235","https://openalex.org/W2051363478"],"abstract_inverted_index":{"Humans":[0],"make":[1],"extensive":[2],"use":[3],"of":[4,125,137,144,158],"auditory":[5,28,40,109,149],"cues":[6],"to":[7,32,55,78,140,154],"interact":[8,72],"with":[9,62,73,174],"other":[10],"humans,":[11],"especially":[12],"in":[13,25,38,84,113,146,172],"challenging":[14],"real-world":[15],"acoustic":[16,20,115,128],"environments.":[17,116],"Multiple":[18],"distinct":[19],"events":[21],"usually":[22],"mix":[23],"together":[24],"a":[26,43,122],"complex":[27,39,148],"scene.":[29,150],"The":[30,151],"ability":[31],"separate":[33],"and":[34,57,94],"localize":[35],"mixed":[36],"sound":[37],"scenes":[41],"remains":[42],"demanding":[44],"skill":[45],"for":[46],"binaural":[47,51],"robots.":[48],"In":[49,117],"fact,":[50],"robots":[52,70],"are":[53,92,97],"required":[54],"disambiguate":[56],"interpret":[58],"the":[59,67,82,85,102,132,142,147,156],"environmental":[60],"scene":[61],"only":[63],"two":[64],"sensors.":[65],"At":[66],"same":[68],"time,":[69],"that":[71,130],"humans":[74],"should":[75],"be":[76],"able":[77],"gain":[79],"insights":[80],"about":[81],"speakers":[83,91,145],"environment,":[86],"such":[87],"as":[88],"how":[89,167],"many":[90],"present":[93],"where":[95],"they":[96],"located.":[98],"For":[99],"this":[100,118,159,169],"reason,":[101],"speech":[103,139],"signal":[104],"is":[105,171],"distinctly":[106],"important":[107],"among":[108],"stimuli":[110],"commonly":[111],"found":[112],"human-centered":[114],"paper,":[119],"we":[120,165],"propose":[121],"Bayesian":[123],"method":[124,170],"selectively":[126],"processing":[127],"data":[129],"exploits":[131],"characteristic":[133],"amplitude":[134,180],"envelope":[135],"dynamics":[136,162],"human":[138],"infer":[141],"location":[143],"goal":[152],"was":[153],"demonstrate":[155],"effectiveness":[157],"speech-specific":[160],"temporal":[161],"approach.":[163],"Further,":[164],"measure":[166],"effective":[168],"comparison":[173],"more":[175],"traditional":[176],"methods":[177],"based":[178],"on":[179],"detection":[181],"only.":[182]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}