{"id":"https://openalex.org/W4372260406","doi":"https://doi.org/10.1109/icassp49357.2023.10096667","title":"3D Audio Signal Processing Systems for Speech Enhancement and Sound Localization and Detection","display_name":"3D Audio Signal Processing Systems for Speech Enhancement and Sound Localization and Detection","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260406","doi":"https://doi.org/10.1109/icassp49357.2023.10096667"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096667","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096667","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":"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/A5027263923","display_name":"Jisheng Bai","orcid":"https://orcid.org/0000-0002-9803-8212"},"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":true,"raw_author_name":"Jisheng Bai","raw_affiliation_strings":["Northwestern Polytechnical University,Joint Laboratory of Environmental Sound Sensing, School of Marine Science and Technology,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Joint Laboratory of Environmental Sound Sensing, School of Marine Science and Technology,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056584987","display_name":"Siwei Huang","orcid":"https://orcid.org/0000-0001-8409-1330"},"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":"Siwei Huang","raw_affiliation_strings":["Northwestern Polytechnical University,Joint Laboratory of Environmental Sound Sensing, School of Marine Science and Technology,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Joint Laboratory of Environmental Sound Sensing, School of Marine Science and Technology,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113113933","display_name":"Han Yin","orcid":null},"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":"Han Yin","raw_affiliation_strings":["Northwestern Polytechnical University,Joint Laboratory of Environmental Sound Sensing, School of Marine Science and Technology,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Joint Laboratory of Environmental Sound Sensing, School of Marine Science and Technology,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101934534","display_name":"Yafei Jia","orcid":null},"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":"Yafei Jia","raw_affiliation_strings":["Northwestern Polytechnical University,Joint Laboratory of Environmental Sound Sensing, School of Marine Science and Technology,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Joint Laboratory of Environmental Sound Sensing, School of Marine Science and Technology,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103175728","display_name":"Mou Wang","orcid":"https://orcid.org/0000-0002-6476-2501"},"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":"Mou Wang","raw_affiliation_strings":["Northwestern Polytechnical University,Joint Laboratory of Environmental Sound Sensing, School of Marine Science and Technology,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Joint Laboratory of Environmental Sound Sensing, School of Marine Science and Technology,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065376714","display_name":"Jianfeng Chen","orcid":"https://orcid.org/0000-0002-7281-7138"},"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":"Jianfeng Chen","raw_affiliation_strings":["Northwestern Polytechnical University,Joint Laboratory of Environmental Sound Sensing, School of Marine Science and Technology,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Joint Laboratory of Environmental Sound Sensing, School of Marine Science and Technology,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5027263923"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":0.8133,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.70013144,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9975000023841858,"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":0.7091822028160095},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.6392743587493896},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.637529194355011},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.605507493019104},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.5369664430618286},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.5248051881790161},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5095529556274414},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4785338342189789},{"id":"https://openalex.org/keywords/sound-recording-and-reproduction","display_name":"Sound recording and reproduction","score":0.4152873754501343},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.23950913548469543},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.20876699686050415},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.11437720060348511},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.06818032264709473},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0660698413848877}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7091822028160095},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.6392743587493896},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.637529194355011},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.605507493019104},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.5369664430618286},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.5248051881790161},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5095529556274414},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4785338342189789},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.4152873754501343},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.23950913548469543},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.20876699686050415},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.11437720060348511},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.06818032264709473},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0660698413848877},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096667","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096667","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2090354597","https://openalex.org/W2990594533","https://openalex.org/W3015199127","https://openalex.org/W3206329344","https://openalex.org/W3213747130"],"related_works":["https://openalex.org/W2289868279","https://openalex.org/W3097613282","https://openalex.org/W4285190997","https://openalex.org/W564807179","https://openalex.org/W2088690926","https://openalex.org/W1590604789","https://openalex.org/W2001939451","https://openalex.org/W1585234643","https://openalex.org/W2969585518","https://openalex.org/W2360384790"],"abstract_inverted_index":{"The":[0,53],"L3DAS23":[1,63],"of":[2],"ICASSP":[3],"Signal":[4],"Processing":[5],"Grand":[6],"Challenge":[7],"encourages":[8],"research":[9],"on":[10,37,61],"3D":[11,17,22,77],"audio":[12],"signal":[13],"processing,":[14],"such":[15],"as":[16],"speech":[18],"enhancement":[19],"(SE)":[20],"and":[21,25,39,45,56,79],"sound":[23],"localization":[24],"detection":[26],"(SELD).":[27],"In":[28],"this":[29],"paper,":[30],"we":[31],"propose":[32],"a":[33,46],"two-stage":[34],"system":[35,48],"based":[36],"DPRNN":[38],"UNet":[40],"for":[41,49,76],"the":[42,50,62,70],"SE":[43,55,78],"task":[44],"Conformer-based":[47],"SELD":[51,57],"task.":[52],"proposed":[54,71],"systems":[58],"are":[59],"evaluated":[60],"blind":[64],"test":[65],"sets.":[66],"Results":[67],"show":[68],"that":[69],"methods":[72],"achieve":[73],"state-of-the-art":[74],"performance":[75],"SELD.":[80]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}