{"id":"https://openalex.org/W4408281431","doi":"https://doi.org/10.1109/tce.2025.3549653","title":"Intelligent Speech Handover for Smart Speakers Through Deep Learning: A Custom Loss Function Approach","display_name":"Intelligent Speech Handover for Smart Speakers Through Deep Learning: A Custom Loss Function Approach","publication_year":2025,"publication_date":"2025-03-10","ids":{"openalex":"https://openalex.org/W4408281431","doi":"https://doi.org/10.1109/tce.2025.3549653"},"language":"en","primary_location":{"id":"doi:10.1109/tce.2025.3549653","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tce.2025.3549653","pdf_url":null,"source":{"id":"https://openalex.org/S126824455","display_name":"IEEE Transactions on Consumer Electronics","issn_l":"0098-3063","issn":["0098-3063","1558-4127"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Consumer Electronics","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/A5010201560","display_name":"Vijaya Nirmala Mitnala","orcid":"https://orcid.org/0000-0002-5039-7443"},"institutions":[{"id":"https://openalex.org/I110002522","display_name":"University of Essex","ror":"https://ror.org/02nkf1q06","country_code":"GB","type":"education","lineage":["https://openalex.org/I110002522"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Vijaya Nirmala Mitnala","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Essex, Colchester, U.K","Department of Computer Science and Engineering, University of Essex, Colchester, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Essex, Colchester, U.K","institution_ids":[]},{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Essex, Colchester, UK","institution_ids":["https://openalex.org/I110002522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048860833","display_name":"Martin J. Reed","orcid":"https://orcid.org/0000-0002-6708-4478"},"institutions":[{"id":"https://openalex.org/I110002522","display_name":"University of Essex","ror":"https://ror.org/02nkf1q06","country_code":"GB","type":"education","lineage":["https://openalex.org/I110002522"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Martin J. Reed","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Essex, Colchester, U.K","Department of Computer Science and Engineering, University of Essex, Colchester, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Essex, Colchester, U.K","institution_ids":[]},{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Essex, Colchester, UK","institution_ids":["https://openalex.org/I110002522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054192915","display_name":"John D. Bicknell","orcid":null},"institutions":[{"id":"https://openalex.org/I1332878012","display_name":"BT Group (United Kingdom)","ror":"https://ror.org/00kv9pj15","country_code":"GB","type":"company","lineage":["https://openalex.org/I1332878012"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"John Bicknell","raw_affiliation_strings":["Research and Development, British Telecommunication Plc, Ipswich, U.K","British Telecommunication Plc, Ipswich, UK"],"affiliations":[{"raw_affiliation_string":"Research and Development, British Telecommunication Plc, Ipswich, U.K","institution_ids":[]},{"raw_affiliation_string":"British Telecommunication Plc, Ipswich, UK","institution_ids":["https://openalex.org/I1332878012"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004586167","display_name":"Joyraj Chakraborty","orcid":"https://orcid.org/0000-0001-7609-1277"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Joyraj Chakraborty","raw_affiliation_strings":["Department of Engineering Science, University of Oxford, Oxford, U.K","Department of Engineering Science, University of Oxford, UK"],"affiliations":[{"raw_affiliation_string":"Department of Engineering Science, University of Oxford, Oxford, U.K","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"Department of Engineering Science, University of Oxford, UK","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5010201560"],"corresponding_institution_ids":["https://openalex.org/I110002522"],"apc_list":null,"apc_paid":null,"fwci":3.122,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.89336436,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"71","issue":"2","first_page":"3143","last_page":"3155"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9797000288963318,"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":0.9797000288963318,"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":0.9718000292778015,"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/computer-science","display_name":"Computer science","score":0.6394904851913452},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5424168705940247},{"id":"https://openalex.org/keywords/handover","display_name":"Handover","score":0.5403845906257629},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4960504472255707},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34064948558807373},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.3207598030567169}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6394904851913452},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5424168705940247},{"id":"https://openalex.org/C111852164","wikidata":"https://www.wikidata.org/wiki/Q1414679","display_name":"Handover","level":2,"score":0.5403845906257629},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4960504472255707},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34064948558807373},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.3207598030567169},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/tce.2025.3549653","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tce.2025.3549653","pdf_url":null,"source":{"id":"https://openalex.org/S126824455","display_name":"IEEE Transactions on Consumer Electronics","issn_l":"0098-3063","issn":["0098-3063","1558-4127"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Consumer Electronics","raw_type":"journal-article"},{"id":"pmh:oai:repository.essex.ac.uk:40474","is_oa":false,"landing_page_url":"https://doi.org/10.1109/TCE.2025.3549653","pdf_url":null,"source":{"id":"https://openalex.org/S4306401236","display_name":"Open Access at Essex (University of Essex)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I110002522","host_organization_name":"University of Essex","host_organization_lineage":["https://openalex.org/I110002522"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W928330370","https://openalex.org/W1494198834","https://openalex.org/W2001105367","https://openalex.org/W2046845112","https://openalex.org/W2055891106","https://openalex.org/W2076122236","https://openalex.org/W2080897413","https://openalex.org/W2098193549","https://openalex.org/W2109689830","https://openalex.org/W2118935932","https://openalex.org/W2129182519","https://openalex.org/W2148564659","https://openalex.org/W2165606149","https://openalex.org/W2171987442","https://openalex.org/W2587246729","https://openalex.org/W2742299865","https://openalex.org/W2749505570","https://openalex.org/W2763188033","https://openalex.org/W2794833149","https://openalex.org/W2800667026","https://openalex.org/W2808484484","https://openalex.org/W2951033593","https://openalex.org/W2974062151","https://openalex.org/W2986978314","https://openalex.org/W2987372735","https://openalex.org/W3021261768","https://openalex.org/W3032821910","https://openalex.org/W3091780448","https://openalex.org/W3092671106","https://openalex.org/W3100777112","https://openalex.org/W3111579993","https://openalex.org/W3202467894","https://openalex.org/W3217410715","https://openalex.org/W3217496205","https://openalex.org/W4231225162","https://openalex.org/W4242138061","https://openalex.org/W4280601128","https://openalex.org/W4286305436","https://openalex.org/W4297501569","https://openalex.org/W4312610635","https://openalex.org/W4313178214","https://openalex.org/W4317892896","https://openalex.org/W4319083901","https://openalex.org/W4366310809","https://openalex.org/W4382202992","https://openalex.org/W4383899954","https://openalex.org/W4386609216","https://openalex.org/W6910546390"],"related_works":["https://openalex.org/W2520149731","https://openalex.org/W1981519115","https://openalex.org/W1985631144","https://openalex.org/W2087123996","https://openalex.org/W3111553259","https://openalex.org/W2103264866","https://openalex.org/W53279813","https://openalex.org/W2115561238","https://openalex.org/W2023203067","https://openalex.org/W2378403302"],"abstract_inverted_index":{"The":[0,76],"consistent":[1],"growth":[2],"of":[3,103,115],"the":[4,71,113,116,121],"smart":[5,21,55,124,158],"speaker":[6,56],"market":[7],"has":[8],"established":[9],"far-field":[10],"speech":[11,49],"communication":[12],"as":[13],"an":[14],"alternative":[15],"to":[16,51,70,130],"traditional":[17],"handsets.":[18],"When":[19],"multiple":[20,98],"speakers":[22],"are":[23],"used,":[24],"a":[25,53,83,90,137,143,151],"mechanism":[26],"for":[27,156],"seamless":[28,46],"handover":[29,66],"is":[30,33,128],"needed,":[31],"which":[32],"not":[34],"currently":[35],"supported.":[36],"This":[37],"paper":[38],"presents":[39],"two":[40],"novel":[41],"contributions":[42],"that,":[43],"together,":[44],"enable":[45],"handover:":[47],"using":[48,142],"signals":[50],"select":[52],"suitable":[54,155],"through":[57],"machine":[58],"learning;":[59],"and,":[60,108],"reduction":[61],"in":[62,119],"media":[63],"disruption":[64],"during":[65],"by":[67],"local":[68],"modifications":[69],"session":[72],"initiation":[73],"protocol":[74],"(SIP).":[75],"proposed":[77,139],"solution":[78],"uses":[79],"prediction":[80],"based":[81],"on":[82],"one-dimensional":[84],"convolutional":[85],"neural":[86],"network":[87],"(1DCNN)":[88],"and":[89,148],"custom":[91],"loss":[92,146],"function.":[93],"A":[94],"comprehensive":[95],"evaluation":[96],"with":[97,150],"datasets":[99],"incorporating":[100],"different":[101],"types":[102],"audio":[104],"signals,":[105],"movement":[106],"loci,":[107],"varying":[109],"room":[110],"scenarios":[111],"demonstrates":[112],"effectiveness":[114],"suggested":[117],"method":[118],"predicting":[120],"most":[122],"appropriate":[123],"speaker.":[125],"Our":[126],"proposal":[127],"shown":[129],"be":[131],"highly":[132],"effective":[133],"when":[134],"compared":[135],"against":[136],"previously":[138],"predictor":[140],"or":[141],"standard":[144],"1DCNN":[145],"function":[147],"operates":[149],"low":[152],"computational":[153],"cost,":[154],"consumer":[157],"speakers.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}