{"id":"https://openalex.org/W4416798603","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249031","title":"DOA Estimation with Lightweight Network on LLM-Aided Simulated Acoustic Scenes","display_name":"DOA Estimation with Lightweight Network on LLM-Aided Simulated Acoustic Scenes","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416798603","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249031"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249031","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-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/A5058264308","display_name":"Haowen Li","orcid":"https://orcid.org/0009-0009-0316-5779"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Haowen Li","raw_affiliation_strings":["Nanyang Technological University,Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102807602","display_name":"Zhengding Luo","orcid":"https://orcid.org/0000-0001-5510-2520"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhengding Luo","raw_affiliation_strings":["Nanyang Technological University,Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007698128","display_name":"Dongyuan Shi","orcid":"https://orcid.org/0000-0003-0768-6386"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongyuan Shi","raw_affiliation_strings":["Northwestern Polytechnical University,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119962984","display_name":"Boxiang Wang","orcid":"https://orcid.org/0009-0001-2323-2301"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Boxiang Wang","raw_affiliation_strings":["Nanyang Technological University,Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069714574","display_name":"Junwei Ji","orcid":"https://orcid.org/0009-0006-4609-5131"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Junwei Ji","raw_affiliation_strings":["Nanyang Technological University,Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085127108","display_name":"Ziyi Yang","orcid":"https://orcid.org/0000-0002-3550-9283"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ziyi Yang","raw_affiliation_strings":["Nanyang Technological University,Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072584895","display_name":"Woon\u2010Seng Gan","orcid":"https://orcid.org/0000-0002-7143-1823"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Woon-Seng Gan","raw_affiliation_strings":["Nanyang Technological University,Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5058264308"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.47808744,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"423","last_page":"428"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9869999885559082,"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":0.9869999885559082,"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/T10931","display_name":"Direction-of-Arrival Estimation Techniques","score":0.002899999963119626,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.0026000000070780516,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7063999772071838},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.6514999866485596},{"id":"https://openalex.org/keywords/direction-of-arrival","display_name":"Direction of arrival","score":0.5127999782562256},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4885999858379364},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.44859999418258667},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4262999892234802},{"id":"https://openalex.org/keywords/impulse-response","display_name":"Impulse response","score":0.41100001335144043},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.3589000105857849}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7728999853134155},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7063999772071838},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.6514999866485596},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5669999718666077},{"id":"https://openalex.org/C172051844","wikidata":"https://www.wikidata.org/wiki/Q5280438","display_name":"Direction of arrival","level":3,"score":0.5127999782562256},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4885999858379364},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.44859999418258667},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4262999892234802},{"id":"https://openalex.org/C72279823","wikidata":"https://www.wikidata.org/wiki/Q1139726","display_name":"Impulse response","level":2,"score":0.41100001335144043},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38280001282691956},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3589000105857849},{"id":"https://openalex.org/C169345407","wikidata":"https://www.wikidata.org/wiki/Q8216221","display_name":"Uncorrelated","level":2,"score":0.3587999939918518},{"id":"https://openalex.org/C70836080","wikidata":"https://www.wikidata.org/wiki/Q837940","display_name":"Impulse (physics)","level":2,"score":0.3492000102996826},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.32820001244544983},{"id":"https://openalex.org/C70710897","wikidata":"https://www.wikidata.org/wiki/Q680081","display_name":"Separable space","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.32280001044273376},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.28790000081062317},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249031","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2024897398","https://openalex.org/W2035083192","https://openalex.org/W2104422351","https://openalex.org/W2137369699","https://openalex.org/W2763188033","https://openalex.org/W2808484484","https://openalex.org/W2883288608","https://openalex.org/W2898268964","https://openalex.org/W2946866946","https://openalex.org/W2963163009","https://openalex.org/W2982083293","https://openalex.org/W3095737053","https://openalex.org/W3162883221","https://openalex.org/W3163881933","https://openalex.org/W4226214458","https://openalex.org/W4372260310","https://openalex.org/W4385486692","https://openalex.org/W4388820300","https://openalex.org/W4389317961","https://openalex.org/W4393294847","https://openalex.org/W4402284121"],"related_works":[],"abstract_inverted_index":{"Direction-of-Arrival":[0],"(DOA)":[1],"estimation":[2,50,89],"is":[3],"critical":[4],"in":[5,15,106],"spatial":[6,69],"audio":[7,70],"and":[8,83,96,117,141],"acoustic":[9,42,121],"signal":[10],"processing,":[11],"with":[12,30,57],"wide-ranging":[13],"applications":[14],"real-world.":[16],"Most":[17],"existing":[18],"DOA":[19,49,78,88,139],"models":[20,63],"are":[21],"trained":[22],"on":[23,80,92],"synthetic":[24,135],"data":[25],"by":[26],"convolving":[27],"clean":[28],"speech":[29],"room":[31],"impulse":[32],"responses":[33],"(RIRs),":[34],"which":[35,65],"limits":[36],"their":[37],"generalizability":[38],"due":[39],"to":[40],"constrained":[41],"diversity.":[43],"In":[44],"this":[45,81],"paper,":[46],"we":[47],"revisit":[48],"using":[51],"a":[52,86,97],"recently":[53],"introduced":[54],"dataset":[55,82],"constructed":[56],"the":[58,131],"assistance":[59],"of":[60,133],"large":[61],"language":[62],"(LLMs),":[64],"provides":[66],"more":[67],"diverse":[68],"scenes.":[71],"We":[72],"benchmark":[73],"several":[74],"representative":[75],"neural":[76],"network-based":[77],"methods":[79],"propose":[84],"LightDOA,":[85],"lightweight":[87],"model":[90],"based":[91],"depthwise":[93],"separable":[94],"convolutions":[95],"gated":[98],"recurrent":[99],"unit,":[100],"specifically":[101],"designed":[102],"for":[103,137,148],"mutil-channel":[104],"input":[105],"varying":[107],"environments.":[108],"Experimental":[109],"results":[110],"show":[111],"that":[112],"LightDOA":[113,143],"achieves":[114],"satisfactory":[115],"accuracy":[116],"robustness":[118],"across":[119],"various":[120],"scenes":[122],"while":[123],"maintaining":[124],"low":[125],"computational":[126],"complexity.":[127],"This":[128],"study":[129],"highlights":[130],"potential":[132],"LLM-assisted":[134],"datasets":[136],"advancing":[138],"research,":[140],"demonstrates":[142],"as":[144],"an":[145],"efficient":[146],"solution":[147],"resource-constrained":[149],"applications.":[150]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-28T00:00:00"}