{"id":"https://openalex.org/W4372263689","doi":"https://doi.org/10.1109/icassp49357.2023.10095472","title":"Improved Deep Speaker Localization and Tracking: Revised Training Paradigm and Controlled Latency","display_name":"Improved Deep Speaker Localization and Tracking: Revised Training Paradigm and Controlled Latency","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372263689","doi":"https://doi.org/10.1109/icassp49357.2023.10095472"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095472","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095472","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://biblio.ugent.be/publication/01H14345VYB63KTHQ8VTXFDWHH/file/01H1436DE7D9CMABPC3PZ4K7XR.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071309390","display_name":"Alexander Bohlender","orcid":"https://orcid.org/0000-0003-1819-0482"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Alexander Bohlender","raw_affiliation_strings":["Ghent University - Imec,IDLab,Department of Electronics and Information Systems,Belgium","Department of Electronics and Information Systems, IDLab, Ghent University - Imec, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University - Imec,IDLab,Department of Electronics and Information Systems,Belgium","institution_ids":["https://openalex.org/I32597200"]},{"raw_affiliation_string":"Department of Electronics and Information Systems, IDLab, Ghent University - Imec, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076089410","display_name":"Liesbeth Roelens","orcid":null},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Liesbeth Roelens","raw_affiliation_strings":["Ghent University - Imec,IDLab,Department of Electronics and Information Systems,Belgium","Department of Electronics and Information Systems, IDLab, Ghent University - Imec, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University - Imec,IDLab,Department of Electronics and Information Systems,Belgium","institution_ids":["https://openalex.org/I32597200"]},{"raw_affiliation_string":"Department of Electronics and Information Systems, IDLab, Ghent University - Imec, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081844255","display_name":"Nilesh Madhu","orcid":"https://orcid.org/0000-0001-9131-3309"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Nilesh Madhu","raw_affiliation_strings":["Ghent University - Imec,IDLab,Department of Electronics and Information Systems,Belgium","Department of Electronics and Information Systems, IDLab, Ghent University - Imec, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University - Imec,IDLab,Department of Electronics and Information Systems,Belgium","institution_ids":["https://openalex.org/I32597200"]},{"raw_affiliation_string":"Department of Electronics and Information Systems, IDLab, Ghent University - Imec, Belgium","institution_ids":["https://openalex.org/I32597200"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I32597200"],"apc_list":null,"apc_paid":null,"fwci":0.4821,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.55870635,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9947999715805054,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.992900013923645,"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/computer-science","display_name":"Computer science","score":0.8061113953590393},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.7079681158065796},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.6000217199325562},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5724907517433167},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5367734432220459},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5315539240837097},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5290058255195618},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5171096324920654},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5045140981674194},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5002140998840332},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.4693242907524109},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4353622496128082},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.33582228422164917},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08888444304466248},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07093924283981323}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8061113953590393},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.7079681158065796},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.6000217199325562},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5724907517433167},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5367734432220459},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5315539240837097},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5290058255195618},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5171096324920654},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5045140981674194},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5002140998840332},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.4693242907524109},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4353622496128082},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.33582228422164917},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08888444304466248},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07093924283981323},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"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/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095472","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095472","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:archive.ugent.be:01H14345VYB63KTHQ8VTXFDWHH","is_oa":true,"landing_page_url":"https://biblio.ugent.be/publication/01H14345VYB63KTHQ8VTXFDWHH","pdf_url":"https://biblio.ugent.be/publication/01H14345VYB63KTHQ8VTXFDWHH/file/01H1436DE7D9CMABPC3PZ4K7XR.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISBN: 9781728163277","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:archive.ugent.be:01H14345VYB63KTHQ8VTXFDWHH","is_oa":true,"landing_page_url":"https://biblio.ugent.be/publication/01H14345VYB63KTHQ8VTXFDWHH","pdf_url":"https://biblio.ugent.be/publication/01H14345VYB63KTHQ8VTXFDWHH/file/01H1436DE7D9CMABPC3PZ4K7XR.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISBN: 9781728163277","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G8050015315","display_name":"Robust speech capture and enhancement using ad hoc distributed microphone arrays by integrating and embedding domain-specific signal models within deep-learning frameworks","funder_award_id":"G081420N","funder_id":"https://openalex.org/F4320321730","funder_display_name":"Fonds Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320321730","display_name":"Fonds Wetenschappelijk Onderzoek","ror":"https://ror.org/03qtxy027"},{"id":"https://openalex.org/F4320327336","display_name":"Vlaamse regering","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4372263689.pdf"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W126779258","https://openalex.org/W1549884461","https://openalex.org/W2030486566","https://openalex.org/W2403891086","https://openalex.org/W2885219692","https://openalex.org/W2908510526","https://openalex.org/W2909607850","https://openalex.org/W2964084166","https://openalex.org/W2982341288","https://openalex.org/W3016120758","https://openalex.org/W3034751264","https://openalex.org/W3108495681","https://openalex.org/W3138975519","https://openalex.org/W3167721750","https://openalex.org/W3197097128","https://openalex.org/W3213559049","https://openalex.org/W4231807801","https://openalex.org/W4287766186","https://openalex.org/W6605165268","https://openalex.org/W6640608466","https://openalex.org/W6757817989","https://openalex.org/W6775759657","https://openalex.org/W6779923105","https://openalex.org/W6796058780"],"related_works":["https://openalex.org/W3162204513","https://openalex.org/W4375867731","https://openalex.org/W2371138613","https://openalex.org/W4377865163","https://openalex.org/W3193857078","https://openalex.org/W2888956734","https://openalex.org/W4315865067","https://openalex.org/W2979433843","https://openalex.org/W3208304128","https://openalex.org/W3000197790"],"abstract_inverted_index":{"Even":[0],"without":[1],"a":[2,18,39,60,94,142],"separate":[3],"tracking":[4],"algorithm,":[5],"the":[6,24,31,91,101,106,127,138],"directions":[7],"of":[8,11,93,111,145],"arrival":[9],"(DOAs)":[10],"moving":[12,54],"talkers":[13],"can":[14],"be":[15,57,116],"estimated":[16],"with":[17,45,122],"deep":[19],"neural":[20],"network":[21],"(DNN)":[22],"when":[23],"movement":[25],"trajectories":[26],"used":[27],"for":[28,41,118],"training":[29,43],"allow":[30],"generalization":[32],"to":[33,84,132],"real":[34,123],"signals.":[35],"Previously,":[36],"we":[37,72,89],"proposed":[38],"framework":[40,75],"generating":[42],"data":[44,129],"time-variant":[46],"source":[47],"activity":[48],"and":[49,148],"sudden":[50],"DOA":[51,135],"changes.":[52],"Slowly":[53],"sources":[55],"could":[56],"seen":[58],"as":[59],"special":[61],"case":[62],"thereof,":[63],"but":[64],"were":[65],"not":[66],"explicitly":[67],"modeled.":[68],"In":[69],"this":[70,74],"paper,":[71],"extend":[73],"by":[76],"using":[77],"small":[78],"jumps":[79],"between":[80],"neighboring":[81],"discrete":[82],"DOAs":[83],"simulate":[85],"gradual":[86],"movements.":[87],"Further,":[88],"investigate":[90],"benefit":[92],"latency":[95],"controlled":[96],"bidirectional":[97],"recurrent":[98],"layer":[99],"in":[100],"DNN":[102],"architecture,":[103],"such":[104],"that":[105,126],"required":[107],"strictly":[108],"limited":[109],"context":[110,140],"future":[112,139],"frames":[113],"may":[114],"still":[115],"acceptable":[117],"real-time":[119],"applications.":[120],"Experiments":[121],"recordings":[124],"show":[125],"revised":[128],"generation":[130],"leads":[131],"more":[133],"continuous":[134],"paths,":[136],"whereas":[137],"enables":[141],"quicker":[143],"detection":[144],"speech":[146],"onsets":[147],"offsets.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}