{"id":"https://openalex.org/W4408352987","doi":"https://doi.org/10.1109/icassp49660.2025.10889345","title":"Neural Directed Speech Enhancement with Dual Microphone Array in High Noise Scenario","display_name":"Neural Directed Speech Enhancement with Dual Microphone Array in High Noise Scenario","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352987","doi":"https://doi.org/10.1109/icassp49660.2025.10889345"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889345","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889345","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5111401285","display_name":"Wen Wen","orcid":"https://orcid.org/0009-0003-1873-7262"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Wen","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020198396","display_name":"Qiang Zhou","orcid":"https://orcid.org/0000-0002-6494-6730"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Zhou","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112125021","display_name":"Yu Xi","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Xi","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100358569","display_name":"Haoyu Li","orcid":"https://orcid.org/0000-0002-7102-8348"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyu Li","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ziqi Gong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziqi Gong","raw_affiliation_strings":["AISpeech Ltd,Suzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AISpeech Ltd,Suzhou,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043098653","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0002-7102-9826"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Yu","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9609000086784363,"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":0.9465000033378601,"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/speech-enhancement","display_name":"Speech enhancement","score":0.80620276927948},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6721782684326172},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.6413558721542358},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.6144129633903503},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6093268990516663},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5464621186256409},{"id":"https://openalex.org/keywords/noise-canceling-microphone","display_name":"Noise-canceling microphone","score":0.49826502799987793},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.47523239254951477},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.42185837030410767},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.41416144371032715},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19329160451889038},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.14207026362419128},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09287518262863159}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.80620276927948},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6721782684326172},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.6413558721542358},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.6144129633903503},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6093268990516663},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5464621186256409},{"id":"https://openalex.org/C36922181","wikidata":"https://www.wikidata.org/wiki/Q7047650","display_name":"Noise-canceling microphone","level":5,"score":0.49826502799987793},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.47523239254951477},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.42185837030410767},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.41416144371032715},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19329160451889038},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.14207026362419128},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09287518262863159},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889345","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889345","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1901129140","https://openalex.org/W2144600569","https://openalex.org/W2568308529","https://openalex.org/W2714487941","https://openalex.org/W2803322398","https://openalex.org/W2892163332","https://openalex.org/W2900893004","https://openalex.org/W2909607850","https://openalex.org/W3126260881","https://openalex.org/W3157899172","https://openalex.org/W3160140981","https://openalex.org/W3207551191","https://openalex.org/W4210452741","https://openalex.org/W4214498238","https://openalex.org/W4221147453","https://openalex.org/W4221149546","https://openalex.org/W4224932156","https://openalex.org/W4225298533","https://openalex.org/W4289752563","https://openalex.org/W4296070366","https://openalex.org/W4315606059","https://openalex.org/W4372267368","https://openalex.org/W4372270656","https://openalex.org/W4372347386","https://openalex.org/W4375928773","https://openalex.org/W4385756463","https://openalex.org/W4388755868","https://openalex.org/W4392904393","https://openalex.org/W4392909391","https://openalex.org/W4392932011","https://openalex.org/W4402111963","https://openalex.org/W4406462011","https://openalex.org/W4408352627","https://openalex.org/W4408354367","https://openalex.org/W6772822194","https://openalex.org/W6790691601","https://openalex.org/W6839581590"],"related_works":["https://openalex.org/W1515932869","https://openalex.org/W2769861442","https://openalex.org/W1654949927","https://openalex.org/W2348931051","https://openalex.org/W1980506188","https://openalex.org/W2109356272","https://openalex.org/W1879255185","https://openalex.org/W2804363668","https://openalex.org/W2963983801","https://openalex.org/W2385432413"],"abstract_inverted_index":{"In":[0],"multi-speaker":[1],"scenarios,":[2],"leveraging":[3],"spatial":[4,42],"features":[5],"is":[6],"essential":[7],"for":[8,137],"enhancing":[9],"target":[10,91,106],"speech.":[11],"While":[12],"with":[13,112,131],"limited":[14],"microphone":[15,116],"arrays,":[16],"developing":[17],"a":[18,40,45,64,114],"compact":[19],"multi-channel":[20,72],"speech":[21,73,121],"enhancement":[22,55,59,77,97],"system":[23],"remains":[24],"challenging,":[25],"especially":[26],"in":[27,119,129],"extremely":[28],"low":[29],"signal-to-noise":[30],"ratio":[31],"(SNR)":[32],"conditions.":[33],"To":[34],"tackle":[35],"this":[36],"issue,":[37],"we":[38,62],"propose":[39],"triple-steering":[41],"selection":[43],"method,":[44],"flexible":[46],"framework":[47],"that":[48],"uses":[49],"three":[50],"steering":[51,86],"vectors":[52,87],"to":[53,100],"guide":[54],"and":[56,74,93,107,123],"determine":[57],"the":[58,75,90,96,101,105],"range.":[60],"Specifically,":[61],"introduce":[63],"causal-directed":[65],"U-Net":[66],"(CDUNet)":[67],"model,":[68],"which":[69],"takes":[70],"raw":[71],"desired":[76],"width":[78],"as":[79],"inputs.":[80],"This":[81],"enables":[82],"dynamic":[83],"adjustment":[84],"of":[85,95],"based":[88],"on":[89],"direction":[92],"fine-tuning":[94],"region":[98],"according":[99],"angular":[102],"separation":[103],"between":[104],"interference":[108],"signals.":[109],"Our":[110],"model":[111],"only":[113],"dual":[115],"array,":[117],"excels":[118],"both":[120],"quality":[122],"downstream":[124],"task":[125],"performance.":[126],"It":[127],"operates":[128],"real-time":[130],"minimal":[132],"parameters,":[133],"making":[134],"it":[135],"ideal":[136],"low-latency,":[138],"on-device":[139],"streaming":[140],"applications.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
