乐胖代购免代理版

{"id":"https://openalex.org/W4319862664","doi":"https://doi.org/10.1109/slt54892.2023.10022488","title":"Spatial-DCCRN: DCCRN Equipped with Frame-Level Angle Feature and Hybrid Filtering for Multi-Channel Speech Enhancement","display_name":"Spatial-DCCRN: DCCRN Equipped with Frame-Level Angle Feature and Hybrid Filtering for Multi-Channel Speech Enhancement","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862664","doi":"https://doi.org/10.1109/slt54892.2023.10022488"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022488","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://arxiv.org/pdf/2210.08802","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017208328","display_name":"Shubo Lv","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"]},{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shubo LV","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an,China","Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010250251","display_name":"Yihui Fu","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":"Yihui Fu","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031232410","display_name":"Yukai Jv","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"]},{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yukai JV","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an,China","Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"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":"Lei Xie","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021314526","display_name":"Weixin Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weixin Zhu","raw_affiliation_strings":["Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035226758","display_name":"Wei Rao","orcid":"https://orcid.org/0000-0002-7237-0874"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Rao","raw_affiliation_strings":["Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084128157","display_name":"Yannan Wang","orcid":"https://orcid.org/0000-0001-7248-4954"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yannan Wang","raw_affiliation_strings":["Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.922,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.998274,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":92},"biblio":{"volume":null,"issue":null,"first_page":"436","last_page":"443"},"is_retracted":false,"is_paratext":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":0.9977,"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/T11309","display_name":"Music and Audio Processing","score":0.9942,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spatial-filter","display_name":"Spatial filter","score":0.5782091},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.49636084},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.4367893}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.75671744},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.62899756},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6078421},{"id":"https://openalex.org/C121475858","wikidata":"https://www.wikidata.org/wiki/Q2735911","display_name":"Spatial filter","level":2,"score":0.5782091},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5752562},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.54039735},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.53115475},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.49636084},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4952983},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.47968718},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.47677213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45022202},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.4367893},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43421176},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.4180042},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.41212505},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24628225},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.21997601},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.18526319},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11363307},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10989475},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.08415443},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022488","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.08802","pdf_url":"http://arxiv.org/pdf/2210.08802","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.08802","pdf_url":"http://arxiv.org/pdf/2210.08802","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[{"score":0.65,"display_name":"Peace, justice, and strong institutions","id":"https://metadata.un.org/sdg/16"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":31,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1569827162","https://openalex.org/W1897240248","https://openalex.org/W2067295501","https://openalex.org/W2219249508","https://openalex.org/W2289480995","https://openalex.org/W2516001803","https://openalex.org/W2900893004","https://openalex.org/W2944972166","https://openalex.org/W2962866211","https://openalex.org/W2963242190","https://openalex.org/W2972802573","https://openalex.org/W2998161426","https://openalex.org/W2998572311","https://openalex.org/W3004309045","https://openalex.org/W3015197852","https://openalex.org/W3016094953","https://openalex.org/W3036601975","https://openalex.org/W3094002217","https://openalex.org/W3095717210","https://openalex.org/W3099330747","https://openalex.org/W3140604720","https://openalex.org/W3145364388","https://openalex.org/W3196940724","https://openalex.org/W3198511309","https://openalex.org/W3198680319","https://openalex.org/W3211438798","https://openalex.org/W3213188934","https://openalex.org/W3213747130","https://openalex.org/W4205689591","https://openalex.org/W4225270933"],"related_works":["https://openalex.org/W3002068412","https://openalex.org/W2810291168","https://openalex.org/W2544894352","https://openalex.org/W2144114631","https://openalex.org/W2098715841","https://openalex.org/W2062994807","https://openalex.org/W2011207778","https://openalex.org/W2008181868","https://openalex.org/W2003169404","https://openalex.org/W1584890139"],"abstract_inverted_index":{"Recently,":[0],"multi-channel":[1,38,73,200],"speech":[2,18,124],"enhancement":[3],"has":[4,164],"drawn":[5],"much":[6],"interest":[7],"due":[8],"to":[9,15,49,93,104,142],"the":[10,82,102,111,121,127,144,149,175,181,199,208],"use":[11,25],"of":[12,26,70,113,151,210],"spatial":[13,27,107],"information":[14,28],"distinguish":[16],"target":[17],"from":[19],"interfering":[20],"signal.":[21],"To":[22],"make":[23],"full":[24],"and":[29,58,79,123,138,156],"neural":[30,40],"network":[31,41],"based":[32],"masking":[33,137],"estimation,":[34],"we":[35,46,85,133],"propose":[36],"a":[37,136,191],"denoising":[39],"-":[42],"Spatial":[43],"DCCRN.":[44],"Firstly,":[45],"extend":[47],"S-DCCRN":[48],"multi":[50],"-channel":[51],"scenario,":[52,183],"aiming":[53],"at":[54],"performing":[55],"cascaded":[56],"sub-channel":[57],"full-channel":[59],"processing":[60],"strategy,":[61],"which":[62,99],"can":[63,100],"model":[64,103,188],"different":[65,211],"channels":[66],"separately.":[67],"Moreover,":[68],"instead":[69],"only":[71,180],"adopting":[72],"spectrum":[74],"or":[75],"concatenating":[76],"first-channel's":[77],"magnitude":[78],"IPD":[80],"as":[81,168,170],"model's":[83],"inputs,":[84],"apply":[86],"an":[87],"angle":[88,96],"feature":[89,97],"extraction":[90],"module":[91],"(AFE)":[92],"extract":[94],"frame-level":[95],"embeddings,":[98],"help":[101],"apparently":[105],"perceive":[106],"information.":[108],"Finally,":[109],"since":[110],"phenomenon":[112],"residual":[114,157],"noise":[115,122,158],"will":[116],"be":[117],"more":[118],"serious":[119],"when":[120],"exist":[125],"in":[126,194],"same":[128],"time":[129],"frequency":[130],"(TF)":[131],"bin,":[132],"particularly":[134],"design":[135],"mapping":[139],"filtering":[140],"method":[141],"substitute":[143],"traditional":[145],"filter-and-sum":[146],"operation,":[147],"with":[148],"purpose":[150],"cascading":[152],"coarsely":[153],"denoising,":[154],"dereverberation":[155],"suppression.":[159],"The":[160],"proposed":[161],"model,":[162],"Spatial-DCCRN,":[163],"surpassed":[165],"EaBNet,":[166],"FasNet":[167],"well":[169],"several":[171],"competitive":[172],"models":[173],"on":[174,198],"L3DAS22":[176],"Challenge":[177,202],"dataset.":[178,203],"Not":[179],"3D":[182],"Spatial-DCCRN":[184],"outperforms":[185],"state-of-the-art":[186],"(SOTA)":[187],"MIMO-UNet":[189],"by":[190],"large":[192],"margin":[193],"multiple":[195],"evaluation":[196],"metrics":[197],"ConferencingSpeech2021":[201],"Ablation":[204],"studies":[205],"also":[206],"demonstrate":[207],"effectiveness":[209],"contributions.":[212]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4319862664","counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2024-12-22T17:23:40.068365","created_date":"2023-02-11"}