{"id":"https://openalex.org/W2515632544","doi":"https://doi.org/10.21437/interspeech.2016-1281","title":"HAPPY Team Entry to NIST OpenSAD Challenge: A Fusion of Short-Term Unsupervised and Segment i-Vector Based Speech Activity Detectors","display_name":"HAPPY Team Entry to NIST OpenSAD Challenge: A Fusion of Short-Term Unsupervised and Segment i-Vector Based Speech Activity Detectors","publication_year":2016,"publication_date":"2016-08-29","ids":{"openalex":"https://openalex.org/W2515632544","doi":"https://doi.org/10.21437/interspeech.2016-1281","mag":"2515632544"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2016-1281","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-1281","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://vbn.aau.dk/da/publications/5bbe2ece-4996-4c4c-8f1a-d6c760a0359b","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043168931","display_name":"Tomi Kinnunen","orcid":"https://orcid.org/0000-0002-4371-7322"},"institutions":[{"id":"https://openalex.org/I175532246","display_name":"University of Eastern Finland","ror":"https://ror.org/00cyydd11","country_code":"FI","type":"education","lineage":["https://openalex.org/I175532246"]},{"id":"https://openalex.org/I4210107997","display_name":"Finland University","ror":"https://ror.org/014rks409","country_code":"FI","type":"education","lineage":["https://openalex.org/I4210107997"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tomi Kinnunen","raw_affiliation_strings":["University of Eastern Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Eastern Finland","institution_ids":["https://openalex.org/I175532246","https://openalex.org/I4210107997"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084640883","display_name":"Alexey Sholokhov","orcid":null},"institutions":[{"id":"https://openalex.org/I175532246","display_name":"University of Eastern Finland","ror":"https://ror.org/00cyydd11","country_code":"FI","type":"education","lineage":["https://openalex.org/I175532246"]},{"id":"https://openalex.org/I4210107997","display_name":"Finland University","ror":"https://ror.org/014rks409","country_code":"FI","type":"education","lineage":["https://openalex.org/I4210107997"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Alexey Sholokhov","raw_affiliation_strings":["University of Eastern Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Eastern Finland","institution_ids":["https://openalex.org/I175532246","https://openalex.org/I4210107997"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010032071","display_name":"Elie Khoury","orcid":"https://orcid.org/0000-0001-9568-3729"},"institutions":[{"id":"https://openalex.org/I4210115819","display_name":"Gidropribor","ror":"https://ror.org/01ftfrf48","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210115819"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Elie Khoury","raw_affiliation_strings":["Pindrop"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pindrop","institution_ids":["https://openalex.org/I4210115819"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061663695","display_name":"Dennis Alexander Lehmann Thomsen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dennis Alexander Lehmann Thomsen","raw_affiliation_strings":["The Faculty of Engineering and Science (TECH)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Faculty of Engineering and Science (TECH)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079693142","display_name":"Md Sahidullah","orcid":"https://orcid.org/0000-0002-0624-2903"},"institutions":[{"id":"https://openalex.org/I175532246","display_name":"University of Eastern Finland","ror":"https://ror.org/00cyydd11","country_code":"FI","type":"education","lineage":["https://openalex.org/I175532246"]},{"id":"https://openalex.org/I4210107997","display_name":"Finland University","ror":"https://ror.org/014rks409","country_code":"FI","type":"education","lineage":["https://openalex.org/I4210107997"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Md. Sahidullah","raw_affiliation_strings":["University of Eastern Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Eastern Finland","institution_ids":["https://openalex.org/I175532246","https://openalex.org/I4210107997"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090108098","display_name":"Zheng\u2010Hua Tan","orcid":"https://orcid.org/0000-0001-6856-8928"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng-Hua Tan","raw_affiliation_strings":["Department of Electronic Systems"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Systems","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2992","last_page":"2996"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9995999932289124,"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":0.9907000064849854,"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/nist","display_name":"NIST","score":0.9201454520225525},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.759598970413208},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6054325103759766},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.6036580204963684},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5234167575836182},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4638960361480713},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41682425141334534},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33841633796691895},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.13084152340888977},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11285066604614258},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10648483037948608}],"concepts":[{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.9201454520225525},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.759598970413208},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6054325103759766},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.6036580204963684},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5234167575836182},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4638960361480713},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41682425141334534},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33841633796691895},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.13084152340888977},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11285066604614258},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10648483037948608},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2016-1281","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-1281","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire/5bbe2ece-4996-4c4c-8f1a-d6c760a0359b","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/5bbe2ece-4996-4c4c-8f1a-d6c760a0359b","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Kinnunen, T, Sholokhov, A, Khoury, E, Thomsen, D A L, Sahidullah, M & Tan, Z-H 2016, HAPPY Team Entry to NIST OpenSAD Challenge : A Fusion of Short-Term Unsupervised and Segment i-Vector Based Speech Activity Detectors. in Interspeech 2016 : September 8\u201312, 2016, San Francisco, USA. ISCA, pp. 2992-2996, Interspeech 2016, San Francisco, CA, United States, 08/09/2016. https://doi.org/10.21437/Interspeech.2016-1281","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:erepo.uef.fi:123456789/4362","is_oa":false,"landing_page_url":"https://erepo.uef.fi/handle/123456789/4362","pdf_url":null,"source":{"id":"https://openalex.org/S4306402418","display_name":"UEF eRepo (University of Eastern Finland)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I175532246","host_organization_name":"University of Eastern Finland","host_organization_lineage":["https://openalex.org/I175532246"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"conferenceObject"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:openaire/5bbe2ece-4996-4c4c-8f1a-d6c760a0359b","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/5bbe2ece-4996-4c4c-8f1a-d6c760a0359b","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Kinnunen, T, Sholokhov, A, Khoury, E, Thomsen, D A L, Sahidullah, M & Tan, Z-H 2016, HAPPY Team Entry to NIST OpenSAD Challenge : A Fusion of Short-Term Unsupervised and Segment i-Vector Based Speech Activity Detectors. in Interspeech 2016 : September 8\u201312, 2016, San Francisco, USA. ISCA, pp. 2992-2996, Interspeech 2016, San Francisco, CA, United States, 08/09/2016. https://doi.org/10.21437/Interspeech.2016-1281","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W1560904098","https://openalex.org/W1563939609","https://openalex.org/W2007119422"],"related_works":["https://openalex.org/W2158491338","https://openalex.org/W2807901368","https://openalex.org/W2133733652","https://openalex.org/W2072658171","https://openalex.org/W2606392311","https://openalex.org/W2320042380","https://openalex.org/W4385956668","https://openalex.org/W2900895161","https://openalex.org/W4380838366","https://openalex.org/W2539884462"],"abstract_inverted_index":{"Speech":[0],"activity":[1],"detection":[2,72,115],"(SAD),":[3],"the":[4,47,86,90],"task":[5],"of":[6,24,71,89,98,108],"locating":[7],"speech":[8],"segments":[9],"from":[10],"a":[11,50,95],"given":[12],"recording,":[13],"remains":[14],"challenging":[15],"under":[16],"acoustically":[17],"degraded":[18],"conditions.":[19],"In":[20],"2015,":[21],"National":[22],"Institute":[23],"Standards":[25],"and":[26,44,62,78],"Technology":[27],"(NIST)":[28],"coordinated":[29],"OpenSAD":[30],"bench-mark.":[31],"We":[32],"summarize":[33],"\u201cHAPPY\u201d":[34],"team":[35],"effort":[36],"to":[37,84],"OpenSAD.":[38],"SADs":[39,59,93],"come":[40],"in":[41,69,100],"both":[42],"unsupervised":[43],"supervised":[45,61,77],"flavors,":[46],"latter":[48],"requiring":[49],"labeled":[51],"training":[52],"set.":[53],"Our":[54],"solution":[55],"fuses":[56],"six":[57,91],"base":[58,92],"(2":[60],"4":[63],"unsupervised).":[64],"The":[65],"individually":[66],"best":[67],"SAD,":[68],"terms":[70],"cost":[73],"function":[74],"(DCF),":[75],"is":[76,110],"uses":[79],"adaptive":[80],"segmentation":[81],"with":[82],"i-vectors":[83],"represent":[85],"segments.":[87],"Fusion":[88],"yields":[94],"relative":[96,106],"decrease":[97,107],"9.3%":[99],"DCF":[101],"over":[102],"this":[103],"SAD.":[104],"Further,":[105],"17.4%":[109],"obtained":[111],"by":[112],"incorporating":[113],"channel":[114],"side":[116],"information.":[117]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
