{"id":"https://openalex.org/W2132498366","doi":"https://doi.org/10.1109/iscslp.2010.5684886","title":"Frame selection of interview channel for NIST speaker recognition evaluation","display_name":"Frame selection of interview channel for NIST speaker recognition evaluation","publication_year":2010,"publication_date":"2010-11-01","ids":{"openalex":"https://openalex.org/W2132498366","doi":"https://doi.org/10.1109/iscslp.2010.5684886","mag":"2132498366"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2010.5684886","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2010.5684886","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 7th International Symposium on Chinese Spoken Language Processing","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/A5100813843","display_name":"Hanwu Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hanwu Sun","raw_affiliation_strings":["Human Language Technology Department, Institute for Infocomm Research, Singapore","Human Language Technology Department, Institute for Infocomm Research, A*STAR, Singapore 138632"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology Department, Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]},{"raw_affiliation_string":"Human Language Technology Department, Institute for Infocomm Research, A*STAR, Singapore 138632","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100749735","display_name":"Bin Ma","orcid":"https://orcid.org/0000-0002-9223-9654"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Bin Ma","raw_affiliation_strings":["Human Language Technology Department, Institute for Infocomm Research, Singapore","Human Language Technology Department, Institute for Infocomm Research, A*STAR, Singapore 138632"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology Department, Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]},{"raw_affiliation_string":"Human Language Technology Department, Institute for Infocomm Research, A*STAR, Singapore 138632","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Human Language Technology Department, Institute for Infocomm Research, Singapore","Human Language Technology Department, Institute for Infocomm Research, A*STAR, Singapore 138632"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology Department, Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]},{"raw_affiliation_string":"Human Language Technology Department, Institute for Infocomm Research, A*STAR, Singapore 138632","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":null,"first_page":"305","last_page":"308"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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/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/T11309","display_name":"Music and Audio Processing","score":0.9966999888420105,"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":0.9260762929916382},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8051064014434814},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7366138100624084},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6787891387939453},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6726666688919067},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.538946270942688},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5068410038948059},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4623514413833618},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4374414086341858},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4371471107006073},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.41013482213020325},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3986293375492096},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3232662081718445},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2846897840499878},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1753665804862976},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11272916197776794},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09772008657455444}],"concepts":[{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.9260762929916382},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8051064014434814},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7366138100624084},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6787891387939453},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6726666688919067},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.538946270942688},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5068410038948059},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4623514413833618},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4374414086341858},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4371471107006073},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.41013482213020325},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3986293375492096},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3232662081718445},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2846897840499878},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1753665804862976},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11272916197776794},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09772008657455444},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2010.5684886","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2010.5684886","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 7th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W79317937","https://openalex.org/W110483337","https://openalex.org/W2041823554","https://openalex.org/W2059254811","https://openalex.org/W2078953162","https://openalex.org/W2128653836","https://openalex.org/W2128986198","https://openalex.org/W2137075158","https://openalex.org/W2144760012","https://openalex.org/W4285719527","https://openalex.org/W6603280604","https://openalex.org/W6665243171"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863","https://openalex.org/W2938358845"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,53],"study":[4,91],"a":[5,90],"front-end":[6],"frame":[7,65,78],"selection":[8,66],"approach":[9,19,147],"for":[10,33,59,167],"the":[11,21,43,50,55,73,77,82,87,97,124,132,146,159,164],"interview":[12,51,88,165],"channel":[13,84],"speaker":[14,34,117,168],"recognition":[15,118],"system.":[16],"This":[17],"new":[18],"keeps":[20],"high":[22,154],"quality":[23,155],"speech":[24,31,74,100,156],"frames":[25,32,101,157],"and":[26,29,106,135,158],"removes":[27],"noisy":[28],"irrelevant":[30],"modeling.":[35],"For":[36],"robust":[37],"voice":[38,162],"activity":[39,75],"detection":[40],"(VAD)":[41],"under":[42],"different":[44],"types":[45],"of":[46],"microphones":[47],"located":[48],"in":[49,86,163],"room,":[52],"adopt":[54],"spectral":[56],"subtraction":[57],"algorithm":[58,67],"noise":[60],"reduction.":[61],"An":[62],"energy":[63],"based":[64,102,115],"is":[68,92,120],"first":[69],"applied":[70],"to":[71,94,122,152],"indicate":[72],"at":[76],"level.":[79],"To":[80],"overcome":[81],"summed":[83],"effects":[85],"condition,":[89],"conducted":[93,130],"effectively":[95],"extract":[96],"relevant":[98,160],"speaker's":[99,161],"on":[103,131],"VAD":[104],"Tags":[105,109],"ASR":[107],"transcript":[108],"provided":[110],"by":[111],"NIST.":[112],"The":[113,127],"eigenchannel":[114],"GMM-SVM":[116],"system":[119],"used":[121],"evaluate":[123],"proposed":[125],"method.":[126],"experiments":[128],"are":[129],"NIST":[133,136],"2008":[134],"2010":[137],"Speaker":[138],"Recognition":[139],"Evaluation":[140],"interview-interview":[141],"conditions.":[142],"It":[143],"demonstrates":[144],"that":[145],"provides":[148],"an":[149],"efficient":[150],"way":[151],"select":[153],"environment":[166],"recognition.":[169]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}