{"id":"https://openalex.org/W7160087681","doi":"https://doi.org/10.1109/access.2026.3689044","title":"Discrete Audio Tokens as a Data-Efficient Representation for Acoustic Traffic Monitoring","display_name":"Discrete Audio Tokens as a Data-Efficient Representation for Acoustic Traffic Monitoring","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7160087681","doi":"https://doi.org/10.1109/access.2026.3689044"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3689044","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3689044","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3689044","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041153116","display_name":"Minhan Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I31419693","display_name":"Kyungpook National University","ror":"https://ror.org/040c17130","country_code":"KR","type":"education","lineage":["https://openalex.org/I31419693"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minhan Kim","raw_affiliation_strings":["School of Electronic and Electrical Engineering, Kyungpook National University, Daegu, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0009-8464-2898","affiliations":[{"raw_affiliation_string":"School of Electronic and Electrical Engineering, Kyungpook National University, Daegu, Republic of Korea","institution_ids":["https://openalex.org/I31419693"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135174571","display_name":"Seokjin Lee","orcid":"https://orcid.org/0000-0001-8220-192X"},"institutions":[{"id":"https://openalex.org/I31419693","display_name":"Kyungpook National University","ror":"https://ror.org/040c17130","country_code":"KR","type":"education","lineage":["https://openalex.org/I31419693"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seokjin Lee","raw_affiliation_strings":["School of Electronic and Electrical Engineering, Kyungpook National University, Daegu, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0001-8220-192X","affiliations":[{"raw_affiliation_string":"School of Electronic and Electrical Engineering, Kyungpook National University, Daegu, Republic of Korea","institution_ids":["https://openalex.org/I31419693"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I31419693"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.60214042,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"65618","last_page":"65632"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.7296000123023987,"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/T11309","display_name":"Music and Audio Processing","score":0.7296000123023987,"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/T10860","display_name":"Speech and Audio Processing","score":0.2176000028848648,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.007000000216066837,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/representation","display_name":"Representation (politics)","score":0.6491000056266785},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.36419999599456787},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.3278000056743622},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.30090001225471497},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.2718000113964081}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7973999977111816},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6491000056266785},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5411999821662903},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.36419999599456787},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35749998688697815},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.3278000056743622},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25119999051094055}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3689044","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3689044","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:da5749abef114bd7aec326d6b92fdff7","is_oa":true,"landing_page_url":"https://doaj.org/article/da5749abef114bd7aec326d6b92fdff7","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 65618-65632 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3689044","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3689044","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Acoustic":[0],"traffic":[1],"monitoring":[2],"involves":[3],"a":[4,27,41,56,87,105,131],"complex":[5,96],"combination":[6],"of":[7,30,58,67,74,78],"subtasks,":[8],"including":[9],"vehicle":[10,13,141],"type":[11,142],"classification,":[12],"counting,":[14],"and":[15,65,113,166],"direction-of-arrival":[16],"estimation.":[17],"Effectively":[18],"training":[19,95,107],"deep":[20,28],"learning":[21],"models":[22],"for":[23,54,94],"these":[24,59],"tasks":[25],"requires":[26],"understanding":[29],"traffic-related":[31],"acoustic":[32],"patterns":[33],"as":[34,36],"well":[35],"extensive,":[37],"accurately":[38],"annotated":[39],"datasets,":[40],"resource":[42],"that":[43,124,156,173],"is":[44],"limited":[45],"in":[46,139],"public":[47],"availability.":[48],"Many":[49],"existing":[50],"datasets":[51],"provide":[52],"labels":[53],"only":[55],"subset":[57],"tasks,":[60],"which":[61],"complicates":[62],"the":[63,71,75,140,177],"development":[64,164],"evaluation":[66],"unified":[68],"models.":[69,184],"While":[70],"recent":[72],"release":[73],"large-scale":[76],"“Sound":[77],"Traffic”":[79],"dataset":[80],"by":[81],"DCASE":[82],"2024":[83],"Task":[84],"10":[85],"provided":[86],"significant":[88],"advancement,":[89],"its":[90],"size":[91],"remains":[92],"insufficient":[93],"neural":[97],"networks":[98],"from":[99,130],"scratch.":[100],"Consequently,":[101],"many":[102],"participants":[103],"employed":[104],"sim-to-real":[106],"strategy—pre-training":[108],"on":[109,115,152],"synthetic":[110],"simulation":[111],"data":[112],"fine-tuning":[114],"real-world":[116],"recordings.":[117],"This":[118],"study":[119],"proposes":[120],"an":[121],"alternative":[122],"method":[123],"leverages":[125],"discrete":[126],"audio":[127],"tokens":[128],"extracted":[129],"pre-trained":[132],"DAC":[133],"to":[134],"replace":[135],"conventional":[136],"mel-spectrogram":[137],"features":[138],"classification":[143],"pipeline.":[144],"Our":[145],"approach":[146],"achieves":[147,176],"competitive":[148],"performance":[149,180],"without":[150],"relying":[151],"simulation-based":[153],"pre-training,":[154],"indicating":[155],"reliable":[157],"results":[158,171],"can":[159],"be":[160],"obtained":[161],"with":[162],"reduced":[163],"time":[165],"computational":[167],"cost.":[168],"Notably,":[169],"experimental":[170],"confirm":[172],"our":[174],"system":[175],"most":[178],"stable":[179],"among":[181],"all":[182],"evaluated":[183]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2026-05-05T00:00:00"}