{"id":"https://openalex.org/W90358879","doi":"https://doi.org/10.21437/interspeech.2004-348","title":"Voice activity detection using global soft decision with mixture of Gaussian model","display_name":"Voice activity detection using global soft decision with mixture of Gaussian model","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W90358879","doi":"https://doi.org/10.21437/interspeech.2004-348","mag":"90358879"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-348","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-348","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","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/A5103010759","display_name":"Kiyoung Park","orcid":"https://orcid.org/0009-0004-8673-7608"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kiyoung Park","raw_affiliation_strings":["Samsung"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045861786","display_name":"Changkyu Choi","orcid":"https://orcid.org/0000-0002-1470-8662"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Changkyu Choi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5049789153","display_name":"Jeongsu Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeongsu Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"965","last_page":"968"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9991999864578247,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9990000128746033,"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/filter-bank","display_name":"Filter bank","score":0.7361931800842285},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.7334091067314148},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6677947640419006},{"id":"https://openalex.org/keywords/probability-density-function","display_name":"Probability density function","score":0.6633797883987427},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.633754551410675},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.6134742498397827},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.5185233354568481},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.4714549481868744},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4547343850135803},{"id":"https://openalex.org/keywords/gaussian-noise","display_name":"Gaussian noise","score":0.43714314699172974},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.4230040907859802},{"id":"https://openalex.org/keywords/gaussian-network-model","display_name":"Gaussian network model","score":0.41983330249786377},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4120520353317261},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35356050729751587},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3047161102294922},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.27757376432418823},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2242932915687561},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.20324090123176575}],"concepts":[{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.7361931800842285},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.7334091067314148},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6677947640419006},{"id":"https://openalex.org/C197055811","wikidata":"https://www.wikidata.org/wiki/Q207522","display_name":"Probability density function","level":2,"score":0.6633797883987427},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.633754551410675},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.6134742498397827},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.5185233354568481},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4714549481868744},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4547343850135803},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.43714314699172974},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4230040907859802},{"id":"https://openalex.org/C166550679","wikidata":"https://www.wikidata.org/wiki/Q263400","display_name":"Gaussian network model","level":3,"score":0.41983330249786377},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4120520353317261},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35356050729751587},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3047161102294922},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.27757376432418823},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2242932915687561},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.20324090123176575},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2004-348","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-348","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.8199999928474426,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W47075184","https://openalex.org/W1570876803","https://openalex.org/W2100555417","https://openalex.org/W2121973264","https://openalex.org/W2165895664"],"related_works":["https://openalex.org/W2350507978","https://openalex.org/W2114026179","https://openalex.org/W2016260880","https://openalex.org/W3162483426","https://openalex.org/W2108641942","https://openalex.org/W2388204628","https://openalex.org/W2194875745","https://openalex.org/W2386749094","https://openalex.org/W2055782493","https://openalex.org/W1505666352"],"abstract_inverted_index":{"An":[0],"improvement":[1],"on":[2],"the":[3,20,27,38,43,48,62,67,76,84,99],"voice":[4],"detection":[5],"algorithm":[6],"using":[7,83],"global":[8],"soft":[9],"decision":[10],"(GSD)":[11],"is":[12,45,66,96],"made":[13],"in":[14,47,56,93],"this":[15],"paper.":[16],"In":[17],"GSD":[18],"method,":[19],"speech":[21,58,102],"and":[22,40],"noise":[23],"are":[24],"modelled":[25],"by":[26],"presumed":[28],"probability":[29,104],"density":[30],"function,":[31],"e.g.":[32],"Gaussian":[33,85,90],"pdf.":[34],"We":[35],"propose":[36],"that":[37,98],"estimation":[39,100],"modelling":[41],"of":[42,50,64,70,72,89,101],"signal":[44],"done":[46],"domain":[49],"filterbank":[51,65],"output":[52,63],"which":[53],"widely":[54],"used":[55],"most":[57],"processing":[59],"applications.":[60],"Since":[61],"weighted":[68],"sum":[69],"outputs":[71],"several":[73],"frequency":[74],"bins,":[75],"signals":[77],"can":[78],"no":[79],"longer":[80],"be":[81],"estimated":[82],"models":[86,91],"but":[87],"mixture":[88],"(GMM)":[92],"general.":[94],"It":[95],"shown":[97],"absence":[103],"with":[105],"GMM":[106],"gives":[107],"better":[108],"performance.":[109]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}