{"id":"https://openalex.org/W4372259947","doi":"https://doi.org/10.1109/icassp49357.2023.10095207","title":"Streaming Multi-Channel Speech Separation with Online Time-Domain Generalized Wiener Filter","display_name":"Streaming Multi-Channel Speech Separation with Online Time-Domain Generalized Wiener Filter","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372259947","doi":"https://doi.org/10.1109/icassp49357.2023.10095207"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095207","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095207","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":"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/A5048439332","display_name":"Yi Luo","orcid":"https://orcid.org/0000-0002-7447-3885"},"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":true,"raw_author_name":"Yi Luo","raw_affiliation_strings":["Tencent AI Lab,Shenzhen,China","Tencent AI Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5048439332"],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"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":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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9991999864578247,"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/T11309","display_name":"Music and Audio Processing","score":0.9987000226974487,"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/computer-science","display_name":"Computer science","score":0.7918037176132202},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.7879397869110107},{"id":"https://openalex.org/keywords/wiener-filter","display_name":"Wiener filter","score":0.6456356644630432},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.6394797563552856},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6265544891357422},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.58783358335495},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.515405535697937},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.44471171498298645},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.4432447850704193},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4376162588596344},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4126126766204834},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35547199845314026},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13498646020889282},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12388968467712402},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.09799876809120178}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7918037176132202},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.7879397869110107},{"id":"https://openalex.org/C18537770","wikidata":"https://www.wikidata.org/wiki/Q25523","display_name":"Wiener filter","level":2,"score":0.6456356644630432},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.6394797563552856},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6265544891357422},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.58783358335495},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.515405535697937},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.44471171498298645},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.4432447850704193},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4376162588596344},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4126126766204834},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35547199845314026},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13498646020889282},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12388968467712402},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.09799876809120178},{"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/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/icassp49357.2023.10095207","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095207","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":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W2078394884","https://openalex.org/W2288645994","https://openalex.org/W2289480995","https://openalex.org/W2568308529","https://openalex.org/W2803583024","https://openalex.org/W2889206679","https://openalex.org/W2889224938","https://openalex.org/W2889411318","https://openalex.org/W2890553422","https://openalex.org/W2891997645","https://openalex.org/W2952218014","https://openalex.org/W2963177459","https://openalex.org/W2964058413","https://openalex.org/W3004309045","https://openalex.org/W3008762051","https://openalex.org/W3015372568","https://openalex.org/W3015788098","https://openalex.org/W3096571892","https://openalex.org/W3099330747","https://openalex.org/W3151596526","https://openalex.org/W3171278394","https://openalex.org/W3198127178","https://openalex.org/W4295308648","https://openalex.org/W4297841846","https://openalex.org/W4375928773","https://openalex.org/W6631190155"],"related_works":["https://openalex.org/W2366527995","https://openalex.org/W2006432333","https://openalex.org/W4287182325","https://openalex.org/W2086006777","https://openalex.org/W2958981368","https://openalex.org/W2884513761","https://openalex.org/W2383612990","https://openalex.org/W2361065066","https://openalex.org/W2362773848","https://openalex.org/W2376212674"],"abstract_inverted_index":{"Most":[0],"existing":[1],"streaming":[2],"neural-network-based":[3],"multi-channel":[4,165,172],"speech":[5,174],"separation":[6,175],"systems":[7],"consist":[8],"of":[9,68],"a":[10,29,82,122],"causal":[11],"network":[12],"architecture":[13],"and":[14,126,131,142],"an":[15,38,118,162],"online":[16,39,52,119,143,155],"spatial":[17,22,48,144],"information":[18,23],"extraction":[19,24],"module.":[20],"The":[21],"module":[25,32,41],"can":[26,73,157],"either":[27],"be":[28,74],"feature":[30],"calculation":[31],"that":[33,42,153],"generates":[34],"cross-channel":[35],"features":[36],"or":[37,46],"beamforming":[40,53,107,150],"explicitly":[43],"performs":[44],"frame-":[45],"chunk-level":[47],"filtering.":[49],"While":[50],"such":[51],"modules":[54,146],"were":[55],"mainly":[56],"proposed":[57],"in":[58,104,147,169],"the":[59,66,78,89,105,114,133,148,154,170],"frequency":[60],"domain,":[61],"recent":[62],"literature":[63],"have":[64],"investigated":[65],"potential":[67],"learnable":[69],"time-domain":[70,90],"methods":[71],"which":[72],"jointly":[75],"optimized":[76],"with":[77,81],"entire":[79],"model":[80],"single":[83],"training":[84,134],"objective.":[85],"Among":[86],"those":[87],"methods,":[88],"generalized":[91],"Wiener":[92,166],"filter":[93,167],"(TD-GWF)":[94],"has":[95],"shown":[96],"performance":[97,160],"gain":[98],"compared":[99],"to":[100,117],"conventional":[101],"frequency-domain":[102,164],"beamformers":[103],"sequential":[106,149],"pipeline.":[108],"In":[109],"this":[110],"paper,":[111],"we":[112,129],"modify":[113],"offline":[115,141,163],"TD-GWF":[116,156],"counterpart":[120],"via":[121],"Sherman-Morrison":[123],"formula-based":[124],"approximation":[125],"introduce":[127],"how":[128],"simplify":[130],"stabilize":[132],"phase.":[135],"Experiment":[136],"results":[137],"on":[138],"applying":[139],"various":[140],"filtering":[145],"pipeline":[151],"show":[152],"obtain":[158],"better":[159],"than":[161],"(FD-MCWF)":[168],"noisy":[171],"reverberant":[173],"task.":[176]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}