{"id":"https://openalex.org/W4416799635","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11248969","title":"Direction-Guided Spatial Attention for Multichannel Speech Enhancement","display_name":"Direction-Guided Spatial Attention for Multichannel Speech Enhancement","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799635","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11248969"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11248969","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11248969","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/A5068044387","display_name":"Shuai Nie","orcid":"https://orcid.org/0000-0002-8078-6829"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shuai Nie","raw_affiliation_strings":["Xiaomi Corporation,China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation,China","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053853035","display_name":"Yaran Chen","orcid":"https://orcid.org/0000-0001-9356-0610"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaran Chen","raw_affiliation_strings":["Xi&#x0027;an Jiaotong-Liverpool University,China"],"affiliations":[{"raw_affiliation_string":"Xi&#x0027;an Jiaotong-Liverpool University,China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001732305","display_name":"Shan Liang","orcid":"https://orcid.org/0000-0002-8068-1904"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shan Liang","raw_affiliation_strings":["Xi&#x0027;an Jiaotong-Liverpool University,China"],"affiliations":[{"raw_affiliation_string":"Xi&#x0027;an Jiaotong-Liverpool University,China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101746187","display_name":"Jiaming Xu","orcid":"https://orcid.org/0000-0001-7635-1059"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaming Xu","raw_affiliation_strings":["Xiaomi Corporation,China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation,China","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107079867","display_name":"Runyu Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runyu Shi","raw_affiliation_strings":["Xiaomi Corporation,China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation,China","institution_ids":["https://openalex.org/I862669128"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5068044387"],"corresponding_institution_ids":["https://openalex.org/I862669128"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.48065921,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"783","last_page":"788"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9941999912261963,"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":0.9941999912261963,"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":0.00139999995008111,"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/T11448","display_name":"Face recognition and analysis","score":0.0008999999845400453,"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/focus","display_name":"Focus (optics)","score":0.7451000213623047},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7174000144004822},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.579800009727478},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41179999709129333},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4075999855995178},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3495999872684479},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.3303999900817871}],"concepts":[{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.7451000213623047},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7174000144004822},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7084000110626221},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6689000129699707},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.579800009727478},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4867999851703644},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41179999709129333},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4075999855995178},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3495999872684479},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3303999900817871},{"id":"https://openalex.org/C2777895490","wikidata":"https://www.wikidata.org/wiki/Q7198848","display_name":"Pitch contour","level":2,"score":0.3158999979496002},{"id":"https://openalex.org/C121475858","wikidata":"https://www.wikidata.org/wiki/Q2735911","display_name":"Spatial filter","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2741999924182892},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C2777121530","wikidata":"https://www.wikidata.org/wiki/Q7512739","display_name":"Signal subspace","level":4,"score":0.26330000162124634},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11248969","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11248969","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1501033557","https://openalex.org/W1552314771","https://openalex.org/W1974387177","https://openalex.org/W2089586791","https://openalex.org/W2141998673","https://openalex.org/W2164502538","https://openalex.org/W2166547995","https://openalex.org/W2168729028","https://openalex.org/W2593116425","https://openalex.org/W2891984996","https://openalex.org/W2900893004","https://openalex.org/W2962866211","https://openalex.org/W2963242190","https://openalex.org/W2971417062","https://openalex.org/W2972802573","https://openalex.org/W2982471419","https://openalex.org/W3097173744","https://openalex.org/W3123802967","https://openalex.org/W3152963531"],"related_works":[],"abstract_inverted_index":{"The":[0],"direction":[1,73,80,98,104,116],"of":[2,33,95,118,131],"target":[3,49,97,103,119],"speech":[4,11,59,133,137],"is":[5,17,25,88],"a":[6,40],"crucial":[7],"clue":[8],"for":[9,58],"multichannel":[10],"enhancement.":[12,60],"But":[13],"its":[14],"real-time":[15],"estimation":[16],"usually":[18],"very":[19],"challenging,":[20],"especially":[21],"when":[22],"the":[23,36,48,71,96,102,115,125,129],"source":[24,50],"moving":[26],"and":[27,51,75,106,135],"in":[28],"far-field":[29,136],"reverb":[30],"environments.":[31],"Instead":[32],"directly":[34],"estimating":[35],"direction,":[37],"we":[38],"propose":[39],"direction-guided":[41],"spatial":[42],"attention":[43,87],"to":[44,65,67,99,112,114],"automatically":[45],"focus":[46,100],"on":[47,101],"incorporate":[52],"it":[53],"into":[54],"masking":[55],"neural":[56,110],"beamformers":[57,62],"Neural":[61],"are":[63],"trained":[64],"learn":[66],"preserve":[68],"signals":[69,77],"from":[70,78],"look":[72],"areas":[74,81],"suppress":[76],"other":[79],"as":[82,84],"much":[83],"possible.":[85],"Spatial":[86],"guided":[89],"by":[90],"an":[91,108],"extra":[92],"classification":[93],"objective":[94],"area":[105,117],"select":[107],"appropriate":[109],"beamformer":[111],"listen":[113],"speech.":[120],"Systematic":[121],"experiments":[122],"demonstrate":[123],"that":[124],"proposed":[126],"approach":[127],"improves":[128],"performances":[130],"both":[132],"enhancement":[134],"recognition":[138],"against":[139],"prior":[140],"methods.":[141],"<sup":[142],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[143,145],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup><sup":[144],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>Corresponding":[146],"Author:":[147],"Yaran":[148],"Chen":[149]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-28T00:00:00"}
