{"id":"https://openalex.org/W4405709611","doi":"https://doi.org/10.1109/iscslp63861.2024.10800169","title":"Quantization-Error-Free Soft Label for 2D Sound Source Localization","display_name":"Quantization-Error-Free Soft Label for 2D Sound Source Localization","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405709611","doi":"https://doi.org/10.1109/iscslp63861.2024.10800169"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800169","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800169","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5032679393","display_name":"Linfeng Feng","orcid":"https://orcid.org/0009-0008-7908-779X"},"institutions":[{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]},{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Linfeng Feng","raw_affiliation_strings":["Institute of Artificial Intelligence (TeleAI), China Telecom"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI), China Telecom","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450091","display_name":"Xiao-Lei Zhang","orcid":"https://orcid.org/0000-0001-7694-193X"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao-Lei Zhang","raw_affiliation_strings":["Institute of Artificial Intelligence (TeleAI), China Telecom"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI), China Telecom","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100740143","display_name":"Xuelong Li","orcid":"https://orcid.org/0000-0002-0019-4197"},"institutions":[{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]},{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuelong Li","raw_affiliation_strings":["Institute of Artificial Intelligence (TeleAI), China Telecom"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI), China Telecom","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5032679393"],"corresponding_institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27122818,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"194","last_page":"198"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9972000122070312,"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":0.9972000122070312,"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":0.9735000133514404,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9556999802589417,"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/quantization","display_name":"Quantization (signal processing)","score":0.6985305547714233},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6550634503364563},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47969624400138855},{"id":"https://openalex.org/keywords/acoustic-source-localization","display_name":"Acoustic source localization","score":0.47349056601524353},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.3479829430580139},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34151172637939453},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3411635160446167},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3032870888710022},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.15291115641593933}],"concepts":[{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.6985305547714233},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6550634503364563},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47969624400138855},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.47349056601524353},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.3479829430580139},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34151172637939453},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3411635160446167},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3032870888710022},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.15291115641593933}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10800169","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800169","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":24,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1555217905","https://openalex.org/W2046317813","https://openalex.org/W2069432516","https://openalex.org/W2113638573","https://openalex.org/W2460742184","https://openalex.org/W2763188033","https://openalex.org/W2885219692","https://openalex.org/W2900893004","https://openalex.org/W2975836787","https://openalex.org/W3132229649","https://openalex.org/W3132830522","https://openalex.org/W3160071434","https://openalex.org/W3182358018","https://openalex.org/W4224918929","https://openalex.org/W4252048180","https://openalex.org/W4296068430","https://openalex.org/W4312096470","https://openalex.org/W4375869206","https://openalex.org/W4402083555","https://openalex.org/W6674330103","https://openalex.org/W6757817989","https://openalex.org/W6792180040","https://openalex.org/W6846810392"],"related_works":["https://openalex.org/W4318566916","https://openalex.org/W3054897025","https://openalex.org/W2905044649","https://openalex.org/W2087073758","https://openalex.org/W1541492535","https://openalex.org/W2802930369","https://openalex.org/W1989730649","https://openalex.org/W4389372176","https://openalex.org/W2043583277","https://openalex.org/W2567489220"],"abstract_inverted_index":{"One":[0],"of":[1,5],"the":[2,27,70,91,96,101],"state-of-the-art":[3],"direction":[4],"arrival":[6],"(DOA)":[7],"estimation":[8],"techniques":[9],"is":[10,32,76],"formulated":[11],"as":[12],"a":[13,54,65],"classification":[14,28,102],"problem":[15],"using":[16],"deep":[17],"learning.":[18],"However,":[19],"it":[20],"inherently":[21],"suffers":[22],"from":[23],"quantization":[24,85,97],"errors":[25],"during":[26],"formulation.":[29],"This":[30],"weakness":[31],"further":[33],"amplified":[34],"in":[35,46,112],"two-dimensional":[36],"(2D)":[37],"sound":[38],"source":[39],"localization":[40],"(SSL).":[41],"To":[42],"address":[43],"this":[44,49],"limitation":[45],"2D":[47],"SSL,":[48],"paper":[50],"aims":[51],"to":[52,77,83],"develop":[53],"quantization-error-free":[55],"training":[56],"objective,":[57],"named":[58],"Unbiased":[59],"Label":[60],"Distribution":[61],"(ULD),":[62],"along":[63],"with":[64],"corresponding":[66],"decoding":[67],"scheme":[68],"for":[69],"predicted":[71],"distribution.":[72],"The":[73],"key":[74],"idea":[75],"use":[78],"multiple":[79],"adjacent":[80],"classes":[81],"jointly":[82],"eliminate":[84],"error.":[86],"Experimental":[87],"results":[88],"show":[89],"that":[90],"proposed":[92],"algorithm":[93],"significantly":[94],"breaks":[95],"error":[98],"limit":[99],"when":[100],"model":[103],"achieves":[104],"high":[105,116],"accuracy.":[106],"It":[107],"also":[108],"demonstrates":[109],"strong":[110],"robustness":[111],"low":[113],"signal-to-noise":[114],"ratio,":[115],"reverberation,":[117],"and":[118],"far-field":[119],"environments.":[120]},"counts_by_year":[],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}
