{"id":"https://openalex.org/W4392903092","doi":"https://doi.org/10.1109/icassp48485.2024.10448000","title":"3S-TSE: Efficient Three-Stage Target Speaker Extraction for Real-Time and Low-Resource Applications","display_name":"3S-TSE: Efficient Three-Stage Target Speaker Extraction for Real-Time and Low-Resource Applications","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903092","doi":"https://doi.org/10.1109/icassp48485.2024.10448000"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448000","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448000","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5103195569","display_name":"Shulin He","orcid":"https://orcid.org/0009-0002-0382-3515"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shulin He","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,China","College of Computer Science, Inner Mongolia University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063136754","display_name":"Jinjiang Liu","orcid":"https://orcid.org/0000-0002-1543-9193"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinjiang Liu","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,China","College of Computer Science, Inner Mongolia University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100348716","display_name":"Hao Li","orcid":"https://orcid.org/0009-0002-2615-2195"},"institutions":[{"id":"https://openalex.org/I211433327","display_name":"Ministry of Natural Resources","ror":"https://ror.org/02kxqx159","country_code":"CN","type":"government","lineage":["https://openalex.org/I211433327","https://openalex.org/I4210127390"]},{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Li","raw_affiliation_strings":["Southern University of Science and Technology,Department of Electrical and Electronic Engineering,Shenzhen,China","Department of Electrical and Electronic Engineering, Southern University of Science and Technology, Shenzhen, China","Key Laboratory of Urban Land Resources Monitoring and Simulation, Ministry of Natural Resources, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology,Department of Electrical and Electronic Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"Key Laboratory of Urban Land Resources Monitoring and Simulation, Ministry of Natural Resources, China","institution_ids":["https://openalex.org/I211433327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397616","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0002-5070-4511"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,China","College of Computer Science, Inner Mongolia University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100405410","display_name":"Fei Chen","orcid":"https://orcid.org/0000-0002-6988-492X"},"institutions":[{"id":"https://openalex.org/I211433327","display_name":"Ministry of Natural Resources","ror":"https://ror.org/02kxqx159","country_code":"CN","type":"government","lineage":["https://openalex.org/I211433327","https://openalex.org/I4210127390"]},{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Chen","raw_affiliation_strings":["Southern University of Science and Technology,Department of Electrical and Electronic Engineering,Shenzhen,China","Department of Electrical and Electronic Engineering, Southern University of Science and Technology, Shenzhen, China","Key Laboratory of Urban Land Resources Monitoring and Simulation, Ministry of Natural Resources, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology,Department of Electrical and Electronic Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"Key Laboratory of Urban Land Resources Monitoring and Simulation, Ministry of Natural Resources, China","institution_ids":["https://openalex.org/I211433327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100693230","display_name":"Xueliang Zhang","orcid":"https://orcid.org/0000-0002-0406-1105"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueliang Zhang","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,China","College of Computer Science, Inner Mongolia University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, China","institution_ids":["https://openalex.org/I2722730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2229,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.76750225,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"421","last_page":"425"},"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/T11309","display_name":"Music 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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8001923561096191},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6402093768119812},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6136182546615601},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5157527923583984},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5149091482162476},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5049198269844055},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.49866485595703125},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.480620801448822},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.42409542202949524},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3918781280517578},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37736251950263977}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8001923561096191},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6402093768119812},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6136182546615601},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5157527923583984},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5149091482162476},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5049198269844055},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.49866485595703125},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.480620801448822},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.42409542202949524},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3918781280517578},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37736251950263977},{"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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:10.1109/icassp48485.2024.10448000","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448000","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.4300000071525574}],"awards":[],"funders":[{"id":"https://openalex.org/F4320330944","display_name":"Nature","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1606614440","https://openalex.org/W2052958516","https://openalex.org/W2082183045","https://openalex.org/W2101609516","https://openalex.org/W2135431242","https://openalex.org/W2141998673","https://openalex.org/W2147665979","https://openalex.org/W2516001803","https://openalex.org/W2563356726","https://openalex.org/W2951130829","https://openalex.org/W2952218014","https://openalex.org/W2973062255","https://openalex.org/W3008003372","https://openalex.org/W3012065388","https://openalex.org/W3015623828","https://openalex.org/W3015636705","https://openalex.org/W3016361963","https://openalex.org/W3097653961","https://openalex.org/W3099330747","https://openalex.org/W3103434036","https://openalex.org/W3105928222","https://openalex.org/W3165776651","https://openalex.org/W3196570692","https://openalex.org/W3198156015","https://openalex.org/W4224918929","https://openalex.org/W4225592424","https://openalex.org/W4372346771","https://openalex.org/W4385822829","https://openalex.org/W4385822857","https://openalex.org/W4385823352","https://openalex.org/W4390480998","https://openalex.org/W6636106077"],"related_works":["https://openalex.org/W1879255185","https://openalex.org/W1977167953","https://openalex.org/W2120442551","https://openalex.org/W2769861442","https://openalex.org/W1980506188","https://openalex.org/W2900122540","https://openalex.org/W4240587264","https://openalex.org/W107154053","https://openalex.org/W2043735059","https://openalex.org/W2041060376"],"abstract_inverted_index":{"Target":[0],"speaker":[1,140],"extraction":[2],"(TSE)":[3],"aims":[4],"to":[5,74,94,116],"isolate":[6],"a":[7,16,59,69,109,133],"specific":[8],"voice":[9],"from":[10],"multiple":[11],"mixed":[12],"speakers":[13],"relying":[14],"on":[15,43],"registerd":[17],"sample.":[18],"Since":[19],"voiceprint":[20],"features":[21],"usually":[22],"vary":[23],"greatly,":[24],"current":[25],"end-to-end":[26],"neural":[27,70],"networks":[28],"require":[29],"large":[30],"model":[31],"parameters":[32],"which":[33],"are":[34],"computational":[35,130],"intensive":[36],"and":[37,57],"impractical":[38],"for":[39,136],"real-time":[40,138],"applications,":[41],"espetially":[42],"resource-constrained":[44],"platforms.":[45],"In":[46],"this":[47],"paper,":[48],"we":[49],"address":[50],"the":[51,66,76,79,84,87,96,113,118],"TSE":[52],"task":[53],"using":[54],"microphone":[55],"array":[56],"introduce":[58],"novel":[60],"three-stage":[61],"solution":[62],"that":[63],"systematically":[64],"decouples":[65],"process:":[67],"First,":[68],"network":[71],"is":[72,92],"trained":[73],"estimate":[75],"direction":[77,85],"of":[78],"target":[80,97,139],"speaker.":[81],"Second,":[82],"with":[83],"determined,":[86],"Generalized":[88],"Sidelobe":[89],"Canceller":[90],"(GSC)":[91],"used":[93],"extract":[95],"speech.":[98,121],"Third,":[99],"an":[100],"Inplace":[101],"Convolutional":[102],"Recurrent":[103],"Neural":[104],"Network":[105],"(ICRN)":[106],"acts":[107],"as":[108],"denoising":[110],"post-processor,":[111],"refining":[112],"GSC":[114],"output":[115],"yield":[117],"final":[119],"separated":[120],"Our":[122],"approach":[123],"delivers":[124],"superior":[125],"performance":[126],"while":[127],"drastically":[128],"reducing":[129],"load,":[131],"setting":[132],"new":[134],"standard":[135],"efficient":[137],"extraction.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}