{"id":"https://openalex.org/W2162235983","doi":"https://doi.org/10.1186/1687-4722-2012-1","title":"A novel voice activity detection based on phoneme recognition using statistical model","display_name":"A novel voice activity detection based on phoneme recognition using statistical model","publication_year":2012,"publication_date":"2012-01-09","ids":{"openalex":"https://openalex.org/W2162235983","doi":"https://doi.org/10.1186/1687-4722-2012-1","mag":"2162235983"},"language":"en","primary_location":{"id":"doi:10.1186/1687-4722-2012-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1687-4722-2012-1","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4722-2012-1","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4722-2012-1","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052354827","display_name":"Xulei Bao","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xulei Bao","raw_affiliation_strings":["Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai 200240, China","Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai 200240, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036446909","display_name":"Jie Zhu","orcid":"https://orcid.org/0000-0003-2133-4651"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Zhu","raw_affiliation_strings":["Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai 200240, China","Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai 200240, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":1.2384,"has_fulltext":true,"cited_by_count":26,"citation_normalized_percentile":{"value":0.83911971,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"2012","issue":"1","first_page":null,"last_page":null},"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":0.998199999332428,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9976999759674072,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.856641411781311},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8098224997520447},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7528146505355835},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.666615903377533},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6361434459686279},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.6320508718490601},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5068886876106262},{"id":"https://openalex.org/keywords/viterbi-decoder","display_name":"Viterbi decoder","score":0.43657442927360535},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.43624159693717957},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4298717677593231},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.4269489049911499},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.3583131432533264},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.32259660959243774},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.2720189094543457},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12511441111564636},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11432251334190369}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.856641411781311},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8098224997520447},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7528146505355835},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.666615903377533},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6361434459686279},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.6320508718490601},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5068886876106262},{"id":"https://openalex.org/C117379686","wikidata":"https://www.wikidata.org/wiki/Q6996459","display_name":"Viterbi decoder","level":3,"score":0.43657442927360535},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.43624159693717957},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4298717677593231},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.4269489049911499},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.3583131432533264},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.32259660959243774},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2720189094543457},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12511441111564636},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11432251334190369},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1186/1687-4722-2012-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1687-4722-2012-1","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4722-2012-1","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1186/1687-4722-2012-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1687-4722-2012-1","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4722-2012-1","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.550000011920929,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2162235983.pdf","grobid_xml":"https://content.openalex.org/works/W2162235983.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W2022186940","https://openalex.org/W2031308096","https://openalex.org/W2062335243","https://openalex.org/W2103738385","https://openalex.org/W2103829944","https://openalex.org/W2106300174","https://openalex.org/W2112994876","https://openalex.org/W2114367729","https://openalex.org/W2122647985","https://openalex.org/W2129120544","https://openalex.org/W2129498120","https://openalex.org/W2130071862","https://openalex.org/W2144252361","https://openalex.org/W2145887942","https://openalex.org/W2149759367","https://openalex.org/W2150946027","https://openalex.org/W2152960771","https://openalex.org/W2162055300","https://openalex.org/W2166607750","https://openalex.org/W2169147844","https://openalex.org/W2170644918","https://openalex.org/W2171875767","https://openalex.org/W2596989490","https://openalex.org/W2604292070"],"related_works":["https://openalex.org/W2102309991","https://openalex.org/W1795315578","https://openalex.org/W2373954783","https://openalex.org/W2133857928","https://openalex.org/W2535886977","https://openalex.org/W2143297499","https://openalex.org/W2356694334","https://openalex.org/W2991144886","https://openalex.org/W2790444905","https://openalex.org/W1843778016"],"abstract_inverted_index":{"In":[0],"this":[1,54],"article,":[2],"a":[3,62,109,115,130],"novel":[4],"voice":[5],"activity":[6],"detection":[7,112],"(VAD)":[8],"approach":[9],"based":[10,18],"on":[11],"phoneme":[12,64],"recognition":[13,152],"using":[14,86],"Gaussian":[15],"Mixture":[16],"Model":[17,21],"Hidden":[19],"Markov":[20],"(HMM/GMM)":[22],"is":[23,57,93,145],"proposed.":[24],"Some":[25],"sophisticated":[26],"speech":[27,138,151],"features":[28],"such":[29],"as":[30,61],"high":[31],"order":[32],"statistics":[33],"(HOS),":[34],"harmonic":[35],"structure":[36],"information":[37],"and":[38,72],"Mel-frequency":[39],"cepstral":[40],"coefficients":[41],"(MFCCs)":[42],"are":[43,76],"employed":[44],"to":[45,66,133],"represent":[46],"each":[47],"speech/non-speech":[48,111],"segment.":[49],"The":[50,89,105],"main":[51],"idea":[52],"of":[53,74,101,118],"new":[55,63],"method":[56,107,132,140],"regarding":[58],"the":[59,67,98,102,136],"non-speech":[60],"corresponding":[65],"conventional":[68,137],"phonemes":[69],"in":[70],"mandarin,":[71],"all":[73],"them":[75],"then":[77],"trained":[78],"under":[79],"maximum":[80,99],"likelihood":[81,100],"principle":[82],"with":[83,122,142],"Baum-Welch":[84],"algorithm":[85,92],"GMM/HMM":[87],"model.":[88],"Viterbi":[90],"decoding":[91],"finally":[94],"used":[95],"for":[96,149],"searching":[97],"observed":[103],"signals.":[104],"proposed":[106],"shows":[108],"higher":[110],"accuracy":[113],"over":[114],"wide":[116],"range":[117],"SNR":[119,156],"regimes":[120],"compared":[121],"some":[123],"existing":[124],"VAD":[125,144],"methods.":[126],"We":[127],"also":[128],"propose":[129],"different":[131],"demonstrate":[134],"that":[135],"enhancement":[139],"only":[141],"accurate":[143],"not":[146],"effective":[147],"enough":[148],"automatic":[150],"(ASR)":[153],"at":[154],"low":[155],"regimes.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}