{"id":"https://openalex.org/W4312986385","doi":"https://doi.org/10.1109/iwaenc53105.2022.9914796","title":"Polynomial Eigenvalue Decomposition-Based Target Speaker Voice Activity Detection in the Presence of Competing Talkers","display_name":"Polynomial Eigenvalue Decomposition-Based Target Speaker Voice Activity Detection in the Presence of Competing Talkers","publication_year":2022,"publication_date":"2022-09-05","ids":{"openalex":"https://openalex.org/W4312986385","doi":"https://doi.org/10.1109/iwaenc53105.2022.9914796"},"language":"en","primary_location":{"id":"doi:10.1109/iwaenc53105.2022.9914796","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc53105.2022.9914796","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Workshop on Acoustic Signal Enhancement (IWAENC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://strathprints.strath.ac.uk/81420/1/Neo_etal_IWAENC2022_Polynomial_eigenvalue_decomposition_based_target_speaker_voice_activity_detection.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016082280","display_name":"Vincent W. Neo","orcid":"https://orcid.org/0000-0003-0731-2157"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Vincent W. Neo","raw_affiliation_strings":["Imperial College London,Department of Electrical and Electronic Engineering,UK","Department of Electrical and Electronic Engineering, Imperial College London, UK"],"affiliations":[{"raw_affiliation_string":"Imperial College London,Department of Electrical and Electronic Engineering,UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045197736","display_name":"Stephan Weiss","orcid":"https://orcid.org/0000-0002-3486-7206"},"institutions":[{"id":"https://openalex.org/I181647926","display_name":"University of Strathclyde","ror":"https://ror.org/00n3w3b69","country_code":"GB","type":"education","lineage":["https://openalex.org/I181647926"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Stephan Weiss","raw_affiliation_strings":["University of Strathclyde,Department of Electronic and Electrical Engineering,Scotland","Department of Electronic and Electrical Engineering, University of Strathclyde, Scotland"],"affiliations":[{"raw_affiliation_string":"University of Strathclyde,Department of Electronic and Electrical Engineering,Scotland","institution_ids":["https://openalex.org/I181647926"]},{"raw_affiliation_string":"Department of Electronic and Electrical Engineering, University of Strathclyde, Scotland","institution_ids":["https://openalex.org/I181647926"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043685273","display_name":"Simon W. McKnight","orcid":null},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon W. McKnight","raw_affiliation_strings":["Imperial College London,Department of Electrical and Electronic Engineering,UK","Department of Electrical and Electronic Engineering, Imperial College London, UK"],"affiliations":[{"raw_affiliation_string":"Imperial College London,Department of Electrical and Electronic Engineering,UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031002666","display_name":"Aidan O. T. Hogg","orcid":"https://orcid.org/0000-0001-5501-7799"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Aidan O. T. Hogg","raw_affiliation_strings":["Imperial College London,Department of Electrical and Electronic Engineering,UK","Department of Electrical and Electronic Engineering, Imperial College London, UK"],"affiliations":[{"raw_affiliation_string":"Imperial College London,Department of Electrical and Electronic Engineering,UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016227729","display_name":"Patrick A. Naylor","orcid":"https://orcid.org/0000-0001-8546-8013"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Patrick A. Naylor","raw_affiliation_strings":["Imperial College London,Department of Electrical and Electronic Engineering,UK","Department of Electrical and Electronic Engineering, Imperial College London, UK"],"affiliations":[{"raw_affiliation_string":"Imperial College London,Department of Electrical and Electronic Engineering,UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5016082280"],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":1.9365,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.86265844,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"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":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":0.998199999332428,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9926999807357788,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7018677592277527},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6665374636650085},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6137279272079468},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5792588591575623},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5365498065948486},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5245074033737183},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.48768293857574463},{"id":"https://openalex.org/keywords/polynomial","display_name":"Polynomial","score":0.4819762110710144},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4722321033477783},{"id":"https://openalex.org/keywords/interference","display_name":"Interference (communication)","score":0.4509172737598419},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.43821367621421814},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.43229204416275024},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.42316746711730957},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32884782552719116},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24689969420433044},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18942749500274658},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.15517780184745789},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08072662353515625},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.0776662528514862}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7018677592277527},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6665374636650085},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6137279272079468},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5792588591575623},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5365498065948486},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5245074033737183},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.48768293857574463},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.4819762110710144},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4722321033477783},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.4509172737598419},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.43821367621421814},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.43229204416275024},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.42316746711730957},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32884782552719116},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24689969420433044},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18942749500274658},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.15517780184745789},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08072662353515625},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0776662528514862},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iwaenc53105.2022.9914796","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc53105.2022.9914796","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Workshop on Acoustic Signal Enhancement (IWAENC)","raw_type":"proceedings-article"},{"id":"pmh:oai:strathprints.strath.ac.uk:81420","is_oa":true,"landing_page_url":"https://strathprints.strath.ac.uk/view/author/70486.html>","pdf_url":"https://strathprints.strath.ac.uk/81420/1/Neo_etal_IWAENC2022_Polynomial_eigenvalue_decomposition_based_target_speaker_voice_activity_detection.pdf","source":{"id":"https://openalex.org/S4306402226","display_name":"Strathprints: The University of Strathclyde institutional repository (University of Strathclyde)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I181647926","host_organization_name":"University of Strathclyde","host_organization_lineage":["https://openalex.org/I181647926"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:spiral.imperial.ac.uk:10044/1/98386","is_oa":false,"landing_page_url":"http://hdl.handle.net/10044/1/98386","pdf_url":null,"source":{"id":"https://openalex.org/S4306401396","display_name":"Spiral (Imperial College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I47508984","host_organization_name":"Imperial College London","host_organization_lineage":["https://openalex.org/I47508984"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Workshop on Acoustic Signal Enhancement (IWAENC)","raw_type":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai:strathprints.strath.ac.uk:81420","is_oa":true,"landing_page_url":"https://strathprints.strath.ac.uk/view/author/70486.html>","pdf_url":"https://strathprints.strath.ac.uk/81420/1/Neo_etal_IWAENC2022_Polynomial_eigenvalue_decomposition_based_target_speaker_voice_activity_detection.pdf","source":{"id":"https://openalex.org/S4306402226","display_name":"Strathprints: The University of Strathclyde institutional repository (University of Strathclyde)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I181647926","host_organization_name":"University of Strathclyde","host_organization_lineage":["https://openalex.org/I181647926"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.47999998927116394,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1927786901","display_name":null,"funder_award_id":"EP/S000631/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5125349196","display_name":null,"funder_award_id":"EP/S035842/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4312986385.pdf","grobid_xml":"https://content.openalex.org/works/W4312986385.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1468912418","https://openalex.org/W1476138438","https://openalex.org/W1560013842","https://openalex.org/W2009649672","https://openalex.org/W2060198758","https://openalex.org/W2094721231","https://openalex.org/W2100555417","https://openalex.org/W2112469598","https://openalex.org/W2127851351","https://openalex.org/W2129120544","https://openalex.org/W2136126519","https://openalex.org/W2146324387","https://openalex.org/W2197404611","https://openalex.org/W2554137461","https://openalex.org/W2766586113","https://openalex.org/W2788735937","https://openalex.org/W2788770315","https://openalex.org/W2888728157","https://openalex.org/W2900252409","https://openalex.org/W2911763465","https://openalex.org/W2918532177","https://openalex.org/W2922300136","https://openalex.org/W2928746352","https://openalex.org/W3008357631","https://openalex.org/W3010830830","https://openalex.org/W3024085360","https://openalex.org/W3025260599","https://openalex.org/W3120679850","https://openalex.org/W3135990229","https://openalex.org/W3137585377","https://openalex.org/W3149699184","https://openalex.org/W3191009323","https://openalex.org/W3193786050","https://openalex.org/W3195328568","https://openalex.org/W3206131716","https://openalex.org/W4297788887","https://openalex.org/W6779429391","https://openalex.org/W6791480293","https://openalex.org/W6798385591","https://openalex.org/W7006044986"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1493012537","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W2175373321","https://openalex.org/W1521049138","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W1999004162","https://openalex.org/W4200596008"],"abstract_inverted_index":{"Voice":[0],"activity":[1],"detection":[2],"(VAD)":[3],"algorithms":[4],"are":[5],"essential":[6],"for":[7,80],"many":[8],"speech":[9,17,19,22],"processing":[10,71],"applications,":[11],"such":[12],"as":[13],"speaker":[14],"diarization,":[15],"automatic":[16],"recognition,":[18],"enhancement,":[20],"and":[21,38,100],"coding.":[23],"With":[24],"a":[25,48,87],"good":[26],"VAD":[27,53],"algorithm,":[28],"non-speech":[29],"segments":[30],"can":[31],"be":[32],"excluded":[33],"to":[34,55,74,110,117],"improve":[35],"the":[36,61,76,82,96,105],"performance":[37],"computation":[39],"of":[40,63,86,108],"these":[41],"applications.":[42],"In":[43],"this":[44],"paper,":[45],"we":[46],"propose":[47],"polynomial":[49],"eigenvalue":[50],"decomposition-based":[51],"target-speaker":[52],"algorithm":[54],"detect":[56],"unseen":[57],"target":[58,88],"speakers":[59],"in":[60,98],"presence":[62,83],"competing":[64],"talkers.":[65],"The":[66,90],"proposed":[67,91],"approach":[68,92],"uses":[69],"frame-based":[70],"across":[72],"multi-microphones":[73],"compute":[75],"syndrome":[77],"energy,":[78],"used":[79],"testing":[81],"or":[84],"absence":[85],"speaker.":[89],"is":[93],"consistently":[94],"among":[95],"best":[97],"F1":[99],"balanced":[101],"accuracy":[102],"scores":[103],"over":[104],"investigated":[106],"range":[107],"signal":[109],"interference":[111],"ratio":[112],"(SIR)":[113],"from":[114],"-10":[115],"dB":[116],"20":[118],"dB.":[119]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
