{"id":"https://openalex.org/W4221164004","doi":"https://doi.org/10.21437/interspeech.2022-159","title":"TaylorBeamformer: Learning All-Neural Beamformer for Multi-Channel Speech Enhancement from Taylor\u2019s Approximation Theory","display_name":"TaylorBeamformer: Learning All-Neural Beamformer for Multi-Channel Speech Enhancement from Taylor\u2019s Approximation Theory","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4221164004","doi":"https://doi.org/10.21437/interspeech.2022-159"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-159","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-159","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5053757616","display_name":"Andong Li","orcid":"https://orcid.org/0000-0003-4094-8448"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Andong Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025635655","display_name":"Guochen Yu","orcid":"https://orcid.org/0000-0002-7179-1044"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guochen Yu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070266277","display_name":"Chengshi Zheng","orcid":"https://orcid.org/0000-0001-5656-994X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chengshi Zheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100711527","display_name":"Xiaodong Li","orcid":"https://orcid.org/0000-0002-4170-0076"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaodong Li","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5053757616"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9637,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.88341232,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5413","last_page":"5417"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9977999925613403,"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"}},{"id":"https://openalex.org/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9897000193595886,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"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/interpretability","display_name":"Interpretability","score":0.7574940323829651},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7426299452781677},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5670557618141174},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5249647498130798},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5080559253692627},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5034996867179871},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.483624130487442},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4501967430114746},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4372022747993469},{"id":"https://openalex.org/keywords/taylor-series","display_name":"Taylor series","score":0.43265342712402344},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3380310535430908},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.332008957862854},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.23544743657112122},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14471495151519775},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11012738943099976},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.09544628858566284}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7574940323829651},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7426299452781677},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5670557618141174},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5249647498130798},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5080559253692627},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5034996867179871},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.483624130487442},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4501967430114746},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4372022747993469},{"id":"https://openalex.org/C158946198","wikidata":"https://www.wikidata.org/wiki/Q131187","display_name":"Taylor series","level":2,"score":0.43265342712402344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3380310535430908},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.332008957862854},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.23544743657112122},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14471495151519775},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11012738943099976},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.09544628858566284},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-159","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-159","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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":0,"referenced_works":[],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W2888392564","https://openalex.org/W4310278675","https://openalex.org/W4388422664","https://openalex.org/W4390569940","https://openalex.org/W4361193272","https://openalex.org/W2963326959","https://openalex.org/W4388685194","https://openalex.org/W4312407344","https://openalex.org/W2894289927"],"abstract_inverted_index":{"While":[0],"existing":[1],"end-to-end":[2,117],"beamformers":[3],"achieve":[4],"impressive":[5],"performance":[6],"in":[7,67],"various":[8],"front-end":[9],"speech":[10,50,113],"processing":[11],"tasks,":[12],"they":[13],"usually":[14],"encapsulate":[15],"the":[16,33,57,64,68,71,81,84,92,96,100,105,112,121,139,149,155],"whole":[17],"process":[18,59],"into":[19,80],"a":[20,37],"black":[21],"box":[22],"and":[23,87,99,127,145],"thus":[24,128],"lack":[25],"adequate":[26],"interpretability.":[27],"As":[28],"an":[29],"attempt":[30],"to":[31,109],"fill":[32],"blank,":[34],"we":[35,77,119],"propose":[36],"novel":[38],"neural":[39],"beamformer":[40],"inspired":[41],"by":[42],"Taylor's":[43],"approximation":[44],"theory":[45],"called":[46],"TaylorBeamformer":[47],"for":[48],"multi-channel":[49],"enhancement.":[51],"The":[52],"core":[53],"idea":[54],"is":[55,102],"that":[56,148],"recovery":[58],"can":[60,129],"be":[61],"formulated":[62],"as":[63,95,104],"spatial":[65,97],"filtering":[66],"neighborhood":[69],"of":[70,83],"input":[72],"mixture.":[73],"Based":[74],"on":[75,138,143],"that,":[76],"decompose":[78],"it":[79],"superimposition":[82],"0th-order":[85],"non-derivative":[86],"high-order":[88],"derivative":[89,122],"terms,":[90],"where":[91],"former":[93],"serves":[94],"filter":[98],"latter":[101],"viewed":[103],"residual":[106],"noise":[107],"canceller":[108],"further":[110],"improve":[111],"quality.":[114],"To":[115],"enable":[116],"training,":[118],"replace":[120],"operations":[123],"with":[124],"trainable":[125],"networks":[126],"learn":[130],"from":[131],"training":[132],"data.":[133],"Extensive":[134],"experiments":[135],"are":[136],"conducted":[137],"synthesized":[140],"dataset":[141],"based":[142],"LibriSpeech":[144],"results":[146],"show":[147],"proposed":[150],"approach":[151],"performs":[152],"favorably":[153],"against":[154],"previous":[156],"advanced":[157],"baselines.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}