{"id":"https://openalex.org/W2407342067","doi":"https://doi.org/10.21437/interspeech.2011-61","title":"Comparison of voice activity detectors for interview speech in NIST speaker recognition evaluation","display_name":"Comparison of voice activity detectors for interview speech in NIST speaker recognition evaluation","publication_year":2011,"publication_date":"2011-08-27","ids":{"openalex":"https://openalex.org/W2407342067","doi":"https://doi.org/10.21437/interspeech.2011-61","mag":"2407342067"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2011-61","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-61","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","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/A5010005310","display_name":"Hon-Bill Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hon-Bill Yu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5068768998","display_name":"Man\u2010Wai Mak","orcid":"https://orcid.org/0000-0001-8854-3760"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Man-Wai Mak","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5010005310"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1837,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.89127464,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2353","last_page":"2356"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9993000030517578,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.9536131620407104},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8288396596908569},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7204339504241943},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6951731443405151},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5292103886604309},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.49548542499542236},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4337462782859802},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4222884774208069},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31735727190971375},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.07314425706863403}],"concepts":[{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.9536131620407104},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8288396596908569},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7204339504241943},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6951731443405151},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5292103886604309},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.49548542499542236},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4337462782859802},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4222884774208069},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31735727190971375},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.07314425706863403}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2011-61","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-61","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"},{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/111711","is_oa":false,"landing_page_url":"http://hdl.handle.net/10397/111711","pdf_url":null,"source":{"id":"https://openalex.org/S4306400205","display_name":"PolyU Institutional Research Archive (Hong Kong Polytechnic University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I14243506","host_organization_name":"Hong Kong Polytechnic University","host_organization_lineage":["https://openalex.org/I14243506"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Conference Paper"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.221.3607","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.221.3607","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.eie.polyu.edu.hk/%7Emwmak/papers/interspeech11a.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.308.7637","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.308.7637","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.eie.polyu.edu.hk/~mwmak/papers/interspeech11a.pdf","raw_type":"text"},{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/44461","is_oa":false,"landing_page_url":"http://hdl.handle.net/10397/44461","pdf_url":null,"source":{"id":"https://openalex.org/S4306400205","display_name":"PolyU Institutional Research Archive (Hong Kong Polytechnic University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I14243506","host_organization_name":"Hong Kong Polytechnic University","host_organization_lineage":["https://openalex.org/I14243506"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.75,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1493163583","https://openalex.org/W2065943308","https://openalex.org/W2122647985","https://openalex.org/W2128986198","https://openalex.org/W2129120544","https://openalex.org/W2131562924","https://openalex.org/W2147147599","https://openalex.org/W2156038773","https://openalex.org/W2170644918","https://openalex.org/W2395747372","https://openalex.org/W2415456441","https://openalex.org/W3120116802"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2294333436","https://openalex.org/W2955597484","https://openalex.org/W2373767407","https://openalex.org/W2653598178","https://openalex.org/W3110551121","https://openalex.org/W2747006289","https://openalex.org/W4252682934","https://openalex.org/W2851491717"],"abstract_inverted_index":{"Interview":[0],"speech":[1,18,38,62,134],"has":[2,19],"become":[3],"an":[4],"important":[5],"part":[6],"of":[7,36,73,88],"the":[8,34,45,71,89,93,107,125,129,132,137],"NIST":[9,41,120,142,157],"Speaker":[10],"Recognition":[11],"Evaluations":[12],"(SREs).":[13],"Unlike":[14],"telephone":[15],"speech,":[16],"interview":[17,37],"substantially":[20],"lower":[21],"signal-to-noise":[22],"ratio,":[23],"which":[24],"necessitates":[25],"robust":[26],"voice":[27],"activity":[28,148],"detection":[29],"(VAD).":[30],"This":[31],"paper":[32,59],"highlights":[33],"characteristics":[35],"files":[39],"in":[40,47,51,96],"SREs":[42],"and":[43,75,114,136],"discusses":[44],"difficulties":[46],"performing":[48],"speech/nonspeech":[49],"segmentation":[50],"these":[52,56],"files.":[53],"To":[54],"overcome":[55,106],"difficulties,":[57],"this":[58],"proposes":[60],"using":[61],"enhancement":[63],"techniques":[64],"as":[65],"a":[66],"pre-processing":[67],"step":[68],"for":[69],"enhancing":[70],"reliability":[72],"energy-based":[74],"statistical-model-based":[76],"VADs.":[77,98],"It":[78],"was":[79],"found":[80],"that":[81,124],"spectral":[82,150],"subtraction":[83],"can":[84],"make":[85],"better":[86],"use":[87],"background":[90,116],"spectrum":[91],"than":[92],"likelihood-ratio":[94],"tests":[95],"statisticalmodel-based":[97],"A":[99],"decision":[100],"strategy":[101],"is":[102],"also":[103],"proposed":[104,126],"to":[105],"undesirable":[108],"effects":[109],"caused":[110],"by":[111,141],"impulsive":[112],"signals":[113],"sinusoidal":[115],"signals.":[117],"Results":[118],"on":[119],"2010":[121],"SRE":[122,143],"show":[123],"VAD":[127],"outperforms":[128],"statistical-modelbased":[130],"VAD,":[131],"ETSI-AMR":[133],"coder,":[135],"ASR":[138],"transcripts":[139],"provided":[140],"Workshop.":[144],"Index":[145],"Terms:":[146],"Voice":[147],"detection,":[149],"subtraction,":[151],"likelihood":[152],"ratio":[153],"tests,":[154],"speaker":[155],"verification,":[156],"SRE.":[158]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
