{"id":"https://openalex.org/W2009010671","doi":"https://doi.org/10.1109/icassp.2013.6638954","title":"Voice activity detection based on frequency modulation of harmonics","display_name":"Voice activity detection based on frequency modulation of harmonics","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2009010671","doi":"https://doi.org/10.1109/icassp.2013.6638954","mag":"2009010671"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6638954","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638954","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5088916925","display_name":"Chung-Chien Hsu","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chung-Chien Hsu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National Chiao Tung University, Taiwan","[Dept. of Electr. & Comput. Eng., Nat. Chiao Tung Univ., Hsinchu, Taiwan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National Chiao Tung University, Taiwan","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"[Dept. of Electr. & Comput. Eng., Nat. Chiao Tung Univ., Hsinchu, Taiwan]","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010616536","display_name":"Tse-En Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tse-En Lin","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National Chiao Tung University, Taiwan","[Dept. of Electr. & Comput. Eng., Nat. Chiao Tung Univ., Hsinchu, Taiwan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National Chiao Tung University, Taiwan","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"[Dept. of Electr. & Comput. Eng., Nat. Chiao Tung Univ., Hsinchu, Taiwan]","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066994160","display_name":"Jian-Hueng Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I92172085","display_name":"Chunghwa Telecom (Taiwan)","ror":"https://ror.org/04f786589","country_code":"TW","type":"company","lineage":["https://openalex.org/I92172085"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jian-Hueng Chen","raw_affiliation_strings":["Telecommunication Laboratories, Chunghwa Telecom Company Limited, Taiwan","Telecommun. Labs., Chunghwa Telecom Co., Ltd., Yangmei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Telecommunication Laboratories, Chunghwa Telecom Company Limited, Taiwan","institution_ids":["https://openalex.org/I92172085"]},{"raw_affiliation_string":"Telecommun. Labs., Chunghwa Telecom Co., Ltd., Yangmei, Taiwan","institution_ids":["https://openalex.org/I92172085"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088864528","display_name":"Tai-Shih Chi","orcid":"https://orcid.org/0000-0002-0584-8399"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tai-Shih Chi","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National Chiao Tung University, Taiwan","[Dept. of Electr. & Comput. Eng., Nat. Chiao Tung Univ., Hsinchu, Taiwan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National Chiao Tung University, Taiwan","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"[Dept. of Electr. & Comput. Eng., Nat. Chiao Tung Univ., Hsinchu, Taiwan]","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8987,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.91068129,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"102","issue":null,"first_page":"6679","last_page":"6683"},"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/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/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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/harmonics","display_name":"Harmonics","score":0.7340900897979736},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.720302164554596},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7162583470344543},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.7086924314498901},{"id":"https://openalex.org/keywords/modulation","display_name":"Modulation (music)","score":0.6294345259666443},{"id":"https://openalex.org/keywords/frequency-modulation","display_name":"Frequency modulation","score":0.5697058439254761},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.5406827926635742},{"id":"https://openalex.org/keywords/activity-detection","display_name":"Activity detection","score":0.46992361545562744},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4277898073196411},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3011661171913147},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.25445088744163513},{"id":"https://openalex.org/keywords/radio-frequency","display_name":"Radio frequency","score":0.15641862154006958},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.15271708369255066},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1286410689353943},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09142610430717468},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.06168094277381897}],"concepts":[{"id":"https://openalex.org/C188414643","wikidata":"https://www.wikidata.org/wiki/Q3001183","display_name":"Harmonics","level":3,"score":0.7340900897979736},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.720302164554596},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7162583470344543},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.7086924314498901},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.6294345259666443},{"id":"https://openalex.org/C11930861","wikidata":"https://www.wikidata.org/wiki/Q181417","display_name":"Frequency modulation","level":3,"score":0.5697058439254761},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.5406827926635742},{"id":"https://openalex.org/C2988656282","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity detection","level":2,"score":0.46992361545562744},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4277898073196411},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3011661171913147},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.25445088744163513},{"id":"https://openalex.org/C74064498","wikidata":"https://www.wikidata.org/wiki/Q3396184","display_name":"Radio frequency","level":2,"score":0.15641862154006958},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.15271708369255066},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1286410689353943},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09142610430717468},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.06168094277381897},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2013.6638954","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638954","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1922223312","https://openalex.org/W1982109178","https://openalex.org/W1997810056","https://openalex.org/W2054139811","https://openalex.org/W2062335243","https://openalex.org/W2106405099","https://openalex.org/W2115717467","https://openalex.org/W2120979206","https://openalex.org/W2126617887","https://openalex.org/W2126693545","https://openalex.org/W2129120544","https://openalex.org/W2130426352","https://openalex.org/W2136577779","https://openalex.org/W2141102245","https://openalex.org/W2149053750","https://openalex.org/W2149759367","https://openalex.org/W2156798212","https://openalex.org/W2295228182","https://openalex.org/W6680339134"],"related_works":["https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W2069501481","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W2103239478","https://openalex.org/W4294771049","https://openalex.org/W1523214805","https://openalex.org/W2168417340"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,88],"voice":[6],"activity":[7],"detection":[8],"(VAD)":[9],"algorithm":[10],"based":[11,44],"on":[12,45],"spectro-temporal":[13,21],"modulation":[14,51],"structures":[15],"of":[16,48,52,76],"input":[17],"sounds.":[18],"A":[19],"multi-resolution":[20],"analysis":[22],"framework":[23],"is":[24],"used":[25],"to":[26],"inspect":[27],"prominent":[28],"speech":[29,41,91],"structures.":[30],"By":[31],"comparing":[32],"with":[33,55],"an":[34],"adaptive":[35],"threshold,":[36],"the":[37,46,49,77,84],"proposed":[38,66],"VAD":[39,67],"distinguishes":[40],"from":[42,87],"non-speech":[43],"energy":[47],"frequency":[50],"harmonics.":[53],"Compared":[54],"three":[56],"standard":[57],"VADs,":[58],"ITU-T":[59],"G.729B,":[60],"ETSI":[61],"AMR1":[62],"and":[63,83],"AMR2,":[64],"our":[65],"significantly":[68],"outperforms":[69],"them":[70],"in":[71,74],"non-stationary":[72],"noises":[73],"terms":[75],"receiver":[78],"operating":[79],"characteristic":[80],"(ROC)":[81],"curves":[82],"recognition":[85,92],"rates":[86],"practical":[89],"distributed":[90],"(DSR)":[93],"system.":[94]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
