{"id":"https://openalex.org/W3185349949","doi":"https://doi.org/10.1109/ro-man50785.2021.9515482","title":"Why talk to people when you can talk to robots? Far-field speaker identification in the wild","display_name":"Why talk to people when you can talk to robots? Far-field speaker identification in the wild","publication_year":2021,"publication_date":"2021-08-08","ids":{"openalex":"https://openalex.org/W3185349949","doi":"https://doi.org/10.1109/ro-man50785.2021.9515482","mag":"3185349949"},"language":"en","primary_location":{"id":"doi:10.1109/ro-man50785.2021.9515482","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man50785.2021.9515482","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 30th IEEE International Conference on Robot & Human Interactive Communication (RO-MAN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://vbn.aau.dk/files/580089818/ROMAN21_botx_speaker_identification.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025864803","display_name":"Galadrielle Humblot-Renaux","orcid":"https://orcid.org/0000-0001-7671-7583"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Galadrielle Humblot-Renaux","raw_affiliation_strings":["Robotics & Automation Group, Department of Materials and Production, Aalborg University, Aalborg East, Denmark","Automation Group, Department of Materials and Production, Aalborg University, Aalborg East, Denmark","Robotics &amp"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics & Automation Group, Department of Materials and Production, Aalborg University, Aalborg East, Denmark","institution_ids":["https://openalex.org/I891191580"]},{"raw_affiliation_string":"Automation Group, Department of Materials and Production, Aalborg University, Aalborg East, Denmark","institution_ids":["https://openalex.org/I891191580"]},{"raw_affiliation_string":"Robotics &amp","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100369763","display_name":"Chen Li","orcid":"https://orcid.org/0000-0001-6249-8957"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Chen Li","raw_affiliation_strings":["Robotics & Automation Group, Department of Materials and Production, Aalborg University, Aalborg East, Denmark","Automation Group, Department of Materials and Production, Aalborg University, Aalborg East, Denmark","Robotics &amp"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics & Automation Group, Department of Materials and Production, Aalborg University, Aalborg East, Denmark","institution_ids":["https://openalex.org/I891191580"]},{"raw_affiliation_string":"Automation Group, Department of Materials and Production, Aalborg University, Aalborg East, Denmark","institution_ids":["https://openalex.org/I891191580"]},{"raw_affiliation_string":"Robotics &amp","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003941679","display_name":"Dimitrios Chrysostomou","orcid":"https://orcid.org/0000-0002-6114-8944"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Dimitrios Chrysostomou","raw_affiliation_strings":["Robotics & Automation Group, Department of Materials and Production, Aalborg University, Aalborg East, Denmark","Robotics &amp","Automation Group, Department of Materials and Production, Aalborg University, Aalborg East, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics & Automation Group, Department of Materials and Production, Aalborg University, Aalborg East, Denmark","institution_ids":["https://openalex.org/I891191580"]},{"raw_affiliation_string":"Robotics &amp","institution_ids":[]},{"raw_affiliation_string":"Automation Group, Department of Materials and Production, Aalborg University, Aalborg East, Denmark","institution_ids":["https://openalex.org/I891191580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I891191580"],"apc_list":null,"apc_paid":null,"fwci":0.4197,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.69241512,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"272","last_page":"278"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10860","display_name":"Speech and Audio Processing","score":0.998199999332428,"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/T12031","display_name":"Speech and dialogue systems","score":0.9965000152587891,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.7356496453285217},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.6520315408706665},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6337521076202393},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6009151935577393},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.540384829044342},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.45015424489974976},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4226105213165283},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3996931314468384},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3316008448600769},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.05010071396827698}],"concepts":[{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.7356496453285217},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.6520315408706665},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6337521076202393},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6009151935577393},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.540384829044342},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.45015424489974976},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4226105213165283},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3996931314468384},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3316008448600769},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.05010071396827698},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ro-man50785.2021.9515482","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man50785.2021.9515482","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 30th IEEE International Conference on Robot & Human Interactive Communication (RO-MAN)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/f1881b35-812d-4a0d-ab1b-4b0794a4f097","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/f1881b35-812d-4a0d-ab1b-4b0794a4f097","pdf_url":"https://vbn.aau.dk/files/580089818/ROMAN21_botx_speaker_identification.pdf","source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Humblot-Renaux , G , Li , C & Chrysostomou , D 2021 , Why talk to people when you can talk to robots? Far-field speaker identification in the wild . in 2021 30th IEEE International Conference on Robot and Human Interactive Communication, RO-MAN 2021 . IEEE , IEEE RO-MAN proceedings , pp. 272-278 , 30th IEEE International Conference on Robot and Human Interactive Communication, RO-MAN 2021 , Virtual, Vancouver , Canada , 08/08/2021 . https://doi.org/10.1109/RO-MAN50785.2021.9515482","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:publications/f1881b35-812d-4a0d-ab1b-4b0794a4f097","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/f1881b35-812d-4a0d-ab1b-4b0794a4f097","pdf_url":"https://vbn.aau.dk/files/580089818/ROMAN21_botx_speaker_identification.pdf","source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Humblot-Renaux , G , Li , C & Chrysostomou , D 2021 , Why talk to people when you can talk to robots? Far-field speaker identification in the wild . in 2021 30th IEEE International Conference on Robot and Human Interactive Communication, RO-MAN 2021 . IEEE , IEEE RO-MAN proceedings , pp. 272-278 , 30th IEEE International Conference on Robot and Human Interactive Communication, RO-MAN 2021 , Virtual, Vancouver , Canada , 08/08/2021 . https://doi.org/10.1109/RO-MAN50785.2021.9515482","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G8441122620","display_name":null,"funder_award_id":"857061","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3185349949.pdf","grobid_xml":"https://content.openalex.org/works/W3185349949.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W1975988780","https://openalex.org/W1982599741","https://openalex.org/W2108598243","https://openalex.org/W2137658434","https://openalex.org/W2194775991","https://openalex.org/W2251372956","https://openalex.org/W2295107390","https://openalex.org/W2465929418","https://openalex.org/W2516764878","https://openalex.org/W2549349626","https://openalex.org/W2604137269","https://openalex.org/W2613364463","https://openalex.org/W2626967530","https://openalex.org/W2737712196","https://openalex.org/W2754721836","https://openalex.org/W2792511626","https://openalex.org/W2792512374","https://openalex.org/W2808631503","https://openalex.org/W2809661872","https://openalex.org/W2884503816","https://openalex.org/W2916104401","https://openalex.org/W2939855790","https://openalex.org/W2946508582","https://openalex.org/W2963263347","https://openalex.org/W2964212410","https://openalex.org/W2972311940","https://openalex.org/W2990081853","https://openalex.org/W3006646738","https://openalex.org/W3019117105","https://openalex.org/W3040329661","https://openalex.org/W3082497237","https://openalex.org/W3096025930","https://openalex.org/W3113823857","https://openalex.org/W3121150787","https://openalex.org/W3123264111","https://openalex.org/W3127686677","https://openalex.org/W4248480789","https://openalex.org/W6676297131","https://openalex.org/W6726497184","https://openalex.org/W6739651123","https://openalex.org/W6777092163","https://openalex.org/W6788947877","https://openalex.org/W6789826613"],"related_works":["https://openalex.org/W4389984014","https://openalex.org/W36105149","https://openalex.org/W2144208207","https://openalex.org/W1509309911","https://openalex.org/W2545131480","https://openalex.org/W2249138175","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W4401661962","https://openalex.org/W2096510939"],"abstract_inverted_index":{"Equipping":[0],"robots":[1],"with":[2,102,139,193],"the":[3,113,140,157,179],"ability":[4],"to":[5,10,32,45,75,147,164,186],"identify":[6],"who":[7],"is":[8,12,213],"talking":[9],"them":[11],"an":[13,69],"important":[14],"step":[15],"towards":[16],"natural":[17,36],"and":[18,39,97,168,204,221,228],"effective":[19],"verbal":[20],"interaction.":[21],"However,":[22],"speaker":[23,48,190],"identification":[24,49],"for":[25,50,127],"voice":[26],"control":[27],"remains":[28],"largely":[29],"unexplored":[30],"compared":[31],"recent":[33],"progress":[34],"in":[35,54,87,145,151,172,223,231],"language":[37],"instruction":[38],"speech":[40],"recognition.":[41],"This":[42],"motivates":[43],"us":[44,74],"tackle":[46],"text-independent":[47],"human-robot":[51],"interaction":[52],"applications":[53],"industrial":[55,234],"environments.":[56],"By":[57],"representing":[58],"audio":[59,115],"segments":[60],"as":[61,68],"time-frequency":[62],"spectrograms,":[63],"this":[64],"can":[65],"be":[66],"formulated":[67],"image":[70],"classification":[71],"task,":[72],"allowing":[73],"apply":[76],"state-of-the-art":[77],"convolutional":[78],"neural":[79],"network":[80],"(CNN)":[81],"architectures.":[82],"To":[83],"achieve":[84,187],"robust":[85],"prediction":[86],"unconstrained,":[88],"challenging":[89],"acoustic":[90,174],"conditions,":[91],"we":[92,137,155,183],"take":[93],"a":[94,99,103,132,194,217,224,232],"data-driven":[95],"approach":[96],"collect":[98],"custom":[100],"dataset":[101],"far-field":[104],"microphone":[105],"array,":[106],"featuring":[107],"over":[108],"3":[109],"hours":[110],"of":[111,153],"\"in":[112],"wild\"":[114],"recordings":[116],"from":[117],"six":[118],"speakers,":[119],"which":[120,136,199],"are":[121,184],"then":[122],"encoded":[123],"into":[124,216],"spectral":[125],"images":[126],"CNN-based":[128],"classification.":[129],"We":[130],"propose":[131],"shallow":[133],"3-layer":[134],"CNN,":[135],"compare":[138],"widely":[141],"used":[142,159],"ResNet-18":[143,177],"architecture:":[144],"addition":[146],"benchmarking":[148],"these":[149,161],"models":[150,163],"terms":[152],"accuracy,":[154,182],"visualize":[156],"features":[158,203],"by":[160],"two":[162],"discriminate":[165],"between":[166],"classes,":[167],"investigate":[169],"their":[170],"reliability":[171],"unseen":[173],"scenes.":[175],"Although":[176],"reaches":[178],"highest":[180],"raw":[181],"able":[185],"remarkable":[188],"online":[189],"recognition":[191],"performance":[192],"much":[195],"more":[196,206],"lightweight":[197],"model":[198],"learns":[200],"lower-level":[201],"vocal":[202],"produces":[205],"reliable":[207],"confidence":[208],"scores.":[209],"The":[210],"proposed":[211],"method":[212],"successfully":[214],"integrated":[215],"robotic":[218],"dialogue":[219],"system":[220],"showcased":[222],"mock":[225],"user":[226],"localization":[227],"authentication":[229],"scenario":[230],"realistic":[233],"environment:":[235],"https://youtu.be/IVtZ8LKJZ7A.":[236]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}