{"id":"https://openalex.org/W160840908","doi":"https://doi.org/10.21437/interspeech.2005-119","title":"Robust voice activity detection based on the entropy of noise-suppressed spectrum","display_name":"Robust voice activity detection based on the entropy of noise-suppressed spectrum","publication_year":2005,"publication_date":"2005-09-04","ids":{"openalex":"https://openalex.org/W160840908","doi":"https://doi.org/10.21437/interspeech.2005-119","mag":"160840908"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2005-119","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","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/A5047353872","display_name":"Zolt\u00e1n T\u00fcske","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zoltan Tuske","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020514527","display_name":"P\u00e9ter Mihajlik","orcid":"https://orcid.org/0000-0001-7532-9773"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peter Mihajlik","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071167626","display_name":"Zolt\u00e1n Tobler","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zoltan Tobler","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5075146981","display_name":"Tibor Fegy\u00f3","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tibor Fegyo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3584,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.78306742,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"245","last_page":"248"},"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9973000288009644,"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/speech-recognition","display_name":"Speech recognition","score":0.7226554751396179},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.7165850400924683},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.7109535336494446},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6381513476371765},{"id":"https://openalex.org/keywords/telephony","display_name":"Telephony","score":0.5915881991386414},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5850571393966675},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4961002767086029},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.44553306698799133},{"id":"https://openalex.org/keywords/noise-spectrum","display_name":"Noise spectrum","score":0.43629199266433716},{"id":"https://openalex.org/keywords/novelty-detection","display_name":"Novelty detection","score":0.41439956426620483},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40696394443511963},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.36561107635498047},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3590281009674072},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1982879936695099},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.14328718185424805}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7226554751396179},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.7165850400924683},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.7109535336494446},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6381513476371765},{"id":"https://openalex.org/C195358072","wikidata":"https://www.wikidata.org/wiki/Q944584","display_name":"Telephony","level":2,"score":0.5915881991386414},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5850571393966675},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4961002767086029},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.44553306698799133},{"id":"https://openalex.org/C2983980114","wikidata":"https://www.wikidata.org/wiki/Q4854529","display_name":"Noise spectrum","level":3,"score":0.43629199266433716},{"id":"https://openalex.org/C2778924833","wikidata":"https://www.wikidata.org/wiki/Q7064603","display_name":"Novelty detection","level":3,"score":0.41439956426620483},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40696394443511963},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.36561107635498047},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3590281009674072},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1982879936695099},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.14328718185424805},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2005-119","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W29020499","https://openalex.org/W182487737","https://openalex.org/W1905983571","https://openalex.org/W1921634150","https://openalex.org/W2119535101","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2183208835","https://openalex.org/W2068868050","https://openalex.org/W2364132456","https://openalex.org/W2075390205","https://openalex.org/W2902799674","https://openalex.org/W2114367729","https://openalex.org/W2046524944","https://openalex.org/W1513906452","https://openalex.org/W2546135844","https://openalex.org/W2002243964"],"abstract_inverted_index":{"A":[0],"novel":[1],"noise":[2,18],"robust":[3],"voice":[4],"activity":[5],"detection":[6],"approach":[7],"is":[8,35],"introduced.":[9],"The":[10,46,65,79],"novelty":[11],"of":[12,21,48,61,85,97,105],"the":[13,22,53,59,106],"method":[14],"that":[15],"it":[16],"uses":[17],"suppressed":[19],"spectrum":[20],"input":[23],"signal":[24],"for":[25],"spectral":[26],"entropy":[27,41],"calculation.":[28],"As":[29],"a":[30,95],"result":[31],"excellent":[32],"end-pointing":[33],"performance":[34],"observed":[36],"based":[37],"on":[38,58,69],"predefined":[39],"global":[40],"threshold":[42],"and":[43,74],"time":[44],"constraints.":[45],"effect":[47],"frame":[49],"dropping":[50,84],"controlled":[51],"by":[52],"proposed":[54],"algorithm":[55],"was":[56,88],"investigated":[57],"accuracy":[60],"automatic":[62],"speech":[63,77],"recognition.":[64],"experiments":[66],"were":[67,108],"performed":[68],"Hungarian":[70],"publicly":[71],"available":[72],"noisy":[73],"normal":[75],"telephony":[76],"databases.":[78],"relative":[80],"improvement":[81],"due":[82],"to":[83],"non-speech":[86],"frames":[87,107],"positive":[89],"in":[90,100],"all":[91],"test":[92],"configurations":[93],"with":[94],"maximum":[96],"29,5%.":[98],"Besides,":[99],"average":[101],"more":[102],"than":[103],"50%":[104],"dropped.":[109]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
