{"id":"https://openalex.org/W4405754159","doi":"https://doi.org/10.1109/tmm.2024.3521737","title":"STNet: Deep Audio\u2013Visual Fusion Network for Robust Speaker Tracking","display_name":"STNet: Deep Audio\u2013Visual Fusion Network for Robust Speaker Tracking","publication_year":2024,"publication_date":"2024-12-24","ids":{"openalex":"https://openalex.org/W4405754159","doi":"https://doi.org/10.1109/tmm.2024.3521737"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2024.3521737","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3521737","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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/A5071411382","display_name":"Yidi Li","orcid":"https://orcid.org/0000-0002-5236-7010"},"institutions":[{"id":"https://openalex.org/I9086337","display_name":"Taiyuan University of Technology","ror":"https://ror.org/03kv08d37","country_code":"CN","type":"education","lineage":["https://openalex.org/I9086337"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yidi Li","raw_affiliation_strings":["College of Computer Science and Technology, Taiyuan University of Technology, Taiyuan, China"],"raw_orcid":"https://orcid.org/0000-0002-5236-7010","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Taiyuan University of Technology, Taiyuan, China","institution_ids":["https://openalex.org/I9086337"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hong Liu","orcid":"https://orcid.org/0000-0002-7498-6541"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Liu","raw_affiliation_strings":["Key Laboratory of Machine Perception, Shenzhen Graduate School, Peking University, Beijing, China","Key Laboratory of Machine Perception, Peking University, Shenzhen Graduate School, China"],"raw_orcid":"https://orcid.org/0000-0002-7498-6541","affiliations":[{"raw_affiliation_string":"Key Laboratory of Machine Perception, Shenzhen Graduate School, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Key Laboratory of Machine Perception, Peking University, Shenzhen Graduate School, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086513946","display_name":"Bing Yang","orcid":"https://orcid.org/0000-0002-8978-2322"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Yang","raw_affiliation_strings":["Westlake Institute for Advanced Study, Westlake University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-8978-2322","affiliations":[{"raw_affiliation_string":"Westlake Institute for Advanced Study, Westlake University, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2495,"currency":"USD","value_usd":2495},"apc_paid":null,"fwci":2.3923,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.90125818,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"27","issue":null,"first_page":"1835","last_page":"1847"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9825000166893005,"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":0.9574000239372253,"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":0.8696204423904419},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5491214394569397},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48886817693710327},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4595879316329956},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.4332467317581177},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.42199933528900146},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.41493383049964905},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33040326833724976},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.16672760248184204}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8696204423904419},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5491214394569397},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48886817693710327},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4595879316329956},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.4332467317581177},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.42199933528900146},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.41493383049964905},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33040326833724976},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.16672760248184204},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2024.3521737","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3521737","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6691204964","display_name":null,"funder_award_id":"62403345","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W1518556865","https://openalex.org/W1553557502","https://openalex.org/W1908118577","https://openalex.org/W1974793196","https://openalex.org/W2018840451","https://openalex.org/W2023100145","https://openalex.org/W2088725063","https://openalex.org/W2100152238","https://openalex.org/W2116546045","https://openalex.org/W2124781496","https://openalex.org/W2127000566","https://openalex.org/W2129821199","https://openalex.org/W2138414774","https://openalex.org/W2141823335","https://openalex.org/W2142511364","https://openalex.org/W2142612029","https://openalex.org/W2154151281","https://openalex.org/W2159259269","https://openalex.org/W2163141813","https://openalex.org/W2167206042","https://openalex.org/W2167734090","https://openalex.org/W2316138215","https://openalex.org/W2470394683","https://openalex.org/W2517955251","https://openalex.org/W2618530766","https://openalex.org/W2619383789","https://openalex.org/W2660943524","https://openalex.org/W2752604219","https://openalex.org/W2780124704","https://openalex.org/W2884554680","https://openalex.org/W2890952074","https://openalex.org/W2898200825","https://openalex.org/W2918984654","https://openalex.org/W2948127555","https://openalex.org/W2963115079","https://openalex.org/W2964109005","https://openalex.org/W2964207404","https://openalex.org/W2969987364","https://openalex.org/W2970201661","https://openalex.org/W2989954484","https://openalex.org/W3034751264","https://openalex.org/W3091482797","https://openalex.org/W3115827002","https://openalex.org/W3126757411","https://openalex.org/W3130316726","https://openalex.org/W3135222947","https://openalex.org/W3157866890","https://openalex.org/W3161772428","https://openalex.org/W3162293946","https://openalex.org/W3163658555","https://openalex.org/W3170717896","https://openalex.org/W3174042812","https://openalex.org/W3177116139","https://openalex.org/W3199527474","https://openalex.org/W3213737329","https://openalex.org/W3214586131","https://openalex.org/W4200633562","https://openalex.org/W4223499953","https://openalex.org/W4224932924","https://openalex.org/W4225280365","https://openalex.org/W4289665794","https://openalex.org/W4296069282","https://openalex.org/W4312367758","https://openalex.org/W4328114908","https://openalex.org/W4385245566","https://openalex.org/W4385607538","https://openalex.org/W6684845544","https://openalex.org/W6790830454","https://openalex.org/W6857606499"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731","https://openalex.org/W1982289787"],"abstract_inverted_index":{"Audio-visual":[0],"speaker":[1,49,191],"tracking":[2,50,168],"aims":[3],"to":[4,39,91,108,123,151,165],"determine":[5],"the":[6,41,48,52,110,142,146,160,174,181],"location":[7],"of":[8,162],"human":[9],"targets":[10],"in":[11,43,81,95,141,169],"a":[12,18,69,76,86,96,105,117,155],"scene":[13],"using":[14],"signals":[15,59],"captured":[16],"by":[17,28,154],"multi-sensor":[19],"platform,":[20],"whose":[21],"accuracy":[22],"and":[23,57,128,135,176,188],"robustness":[24],"can":[25],"be":[26],"improved":[27],"multi-modal":[29,126,163],"fusion":[30,34,79,143],"methods.":[31],"Recently,":[32],"several":[33],"methods":[35,187],"have":[36],"been":[37,61],"proposed":[38,182],"model":[40,80,107,125],"correlation":[42],"multiple":[44],"modalities.":[45],"However,":[46],"for":[47],"problem,":[51],"cross-modal":[53,118],"interaction":[54],"between":[55,133],"audio":[56,134],"visual":[58,102,136],"hasn't":[60],"well":[62],"exploited.":[63],"To":[64],"this":[65,82],"end,":[66],"we":[67],"present":[68],"novel":[70],"Speaker":[71],"Tracking":[72],"Network":[73],"(STNet)":[74],"with":[75],"deep":[77],"audio-visual":[78,190],"work.":[83],"We":[84],"design":[85],"visual-guided":[87],"acoustic":[88,112],"measurement":[89],"method":[90],"fuse":[92],"heterogeneous":[93],"cues":[94],"unified":[97],"localization":[98],"space,":[99],"which":[100,158],"employs":[101],"observations":[103,164],"via":[104],"camera":[106],"construct":[109],"enhanced":[111],"map.":[113],"For":[114],"feature":[115],"fusion,":[116],"attention":[119],"module":[120],"is":[121,138,149],"adopted":[122],"jointly":[124],"contexts":[127],"interactions.":[129],"The":[130],"correlated":[131],"information":[132],"features":[137],"further":[139],"interacted":[140],"model.":[144],"Moreover,":[145],"STNet-based":[147,183],"tracker":[148,184],"applied":[150],"multi-speaker":[152],"cases":[153],"quality-aware":[156],"module,":[157],"evaluates":[159],"reliability":[161],"achieve":[166],"robust":[167],"complex":[170],"scenarios.":[171],"Experiments":[172],"on":[173],"AV16.3":[175],"CAV3D":[177],"datasets":[178],"show":[179],"that":[180],"outperforms":[185],"uni-modal":[186],"state-of-the-art":[189],"trackers.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}