{"id":"https://openalex.org/W2115008841","doi":"https://doi.org/10.1109/jstsp.2010.2057192","title":"Low-Complexity Variable Frame Rate Analysis for Speech Recognition and Voice Activity Detection","display_name":"Low-Complexity Variable Frame Rate Analysis for Speech Recognition and Voice Activity Detection","publication_year":2010,"publication_date":"2010-07-20","ids":{"openalex":"https://openalex.org/W2115008841","doi":"https://doi.org/10.1109/jstsp.2010.2057192","mag":"2115008841"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2010.2057192","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2010.2057192","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-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/A5090108098","display_name":"Zheng\u2010Hua Tan","orcid":"https://orcid.org/0000-0001-6856-8928"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"Zheng-Hua Tan","raw_affiliation_strings":["Department of Electronic Systems, University of Aalborg, Aalborg, Denmark","[Dept. of Electron. Syst., Aalborg Univ., Aalborg, Denmark]"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, University of Aalborg, Aalborg, Denmark","institution_ids":["https://openalex.org/I891191580"]},{"raw_affiliation_string":"[Dept. of Electron. Syst., Aalborg Univ., Aalborg, Denmark]","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109059235","display_name":"B\u00f8rge Lindberg","orcid":"https://orcid.org/0000-0001-5394-8100"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"B\u00f8rge Lindberg","raw_affiliation_strings":["Department of Electronic Systems, University of Aalborg, Aalborg, Denmark","[Dept. of Electron. Syst., Aalborg Univ., Aalborg, Denmark]"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, University of Aalborg, Aalborg, Denmark","institution_ids":["https://openalex.org/I891191580"]},{"raw_affiliation_string":"[Dept. of Electron. Syst., Aalborg Univ., Aalborg, Denmark]","institution_ids":["https://openalex.org/I891191580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5090108098"],"corresponding_institution_ids":["https://openalex.org/I891191580"],"apc_list":null,"apc_paid":null,"fwci":5.4133,"has_fulltext":false,"cited_by_count":98,"citation_normalized_percentile":{"value":0.96374143,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"4","issue":"5","first_page":"798","last_page":"807"},"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":0.9994999766349792,"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":0.9994000196456909,"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/computer-science","display_name":"Computer science","score":0.7808787822723389},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7543416023254395},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6939414739608765},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5496975183486938},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.545415997505188},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.5380752682685852},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5370179414749146},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5124912261962891},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4763753116130829},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.45764774084091187},{"id":"https://openalex.org/keywords/codec2","display_name":"Codec2","score":0.43502023816108704},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.417858749628067},{"id":"https://openalex.org/keywords/maximum-a-posteriori-estimation","display_name":"Maximum a posteriori estimation","score":0.4129682183265686},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39344191551208496},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36184489727020264},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.20736798644065857},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.148197740316391},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09628021717071533},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08286294341087341}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7808787822723389},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7543416023254395},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6939414739608765},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5496975183486938},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.545415997505188},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.5380752682685852},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5370179414749146},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5124912261962891},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4763753116130829},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.45764774084091187},{"id":"https://openalex.org/C75217168","wikidata":"https://www.wikidata.org/wiki/Q1105653","display_name":"Codec2","level":4,"score":0.43502023816108704},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.417858749628067},{"id":"https://openalex.org/C9810830","wikidata":"https://www.wikidata.org/wiki/Q635384","display_name":"Maximum a posteriori estimation","level":3,"score":0.4129682183265686},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39344191551208496},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36184489727020264},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.20736798644065857},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.148197740316391},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09628021717071533},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08286294341087341},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/jstsp.2010.2057192","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2010.2057192","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:publications/4fe578f0-d4ed-11de-bb13-000ea68e967b","is_oa":false,"landing_page_url":"https://vbn.aau.dk/da/publications/4fe578f0-d4ed-11de-bb13-000ea68e967b","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Tan , Z-H & Lindberg , B 2010 , ' Low-Complexity Variable Frame Rate Analysis for Speech Recognition and Voice Activity Detection ' , IEEE Journal of Selected Topics in Signal Processing , vol. 4 , no. 5 , pp. 798-807 . https://doi.org/10.1109/JSTSP.2010.2057192","raw_type":"article"}],"best_oa_location":null,"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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W25451487","https://openalex.org/W72363547","https://openalex.org/W111666610","https://openalex.org/W236951136","https://openalex.org/W1493163583","https://openalex.org/W1528909574","https://openalex.org/W1550527692","https://openalex.org/W1572533133","https://openalex.org/W1837709900","https://openalex.org/W1905983571","https://openalex.org/W1977112032","https://openalex.org/W1984446451","https://openalex.org/W2010377246","https://openalex.org/W2052667477","https://openalex.org/W2066561607","https://openalex.org/W2069976350","https://openalex.org/W2098406627","https://openalex.org/W2101357962","https://openalex.org/W2103738385","https://openalex.org/W2104599461","https://openalex.org/W2110707300","https://openalex.org/W2112772843","https://openalex.org/W2117468249","https://openalex.org/W2124243855","https://openalex.org/W2128653836","https://openalex.org/W2148046258","https://openalex.org/W2151484683","https://openalex.org/W2152051032","https://openalex.org/W2156561020","https://openalex.org/W2158146178","https://openalex.org/W2158336491","https://openalex.org/W2160610099","https://openalex.org/W2163634074","https://openalex.org/W2166533296","https://openalex.org/W2166846144","https://openalex.org/W6601023208","https://openalex.org/W6609071974","https://openalex.org/W6631875079","https://openalex.org/W6633226916","https://openalex.org/W6638754818","https://openalex.org/W6676004468","https://openalex.org/W6676284021","https://openalex.org/W6676879020"],"related_works":["https://openalex.org/W3211091508","https://openalex.org/W1542588102","https://openalex.org/W2151333624","https://openalex.org/W2496295964","https://openalex.org/W4319347033","https://openalex.org/W1572861854","https://openalex.org/W2910493550","https://openalex.org/W1976952689","https://openalex.org/W1984921740","https://openalex.org/W2336887028"],"abstract_inverted_index":{"Frame-based":[0],"speech":[1,9,100,155,173,191,221],"processing":[2,156,222],"inherently":[3],"assumes":[4],"a":[5,12,18,46,55,72,90,113,124],"stationary":[6],"behavior":[7],"of":[8,15,23,65,89],"signals":[10,25],"in":[11,98,176,189],"short":[13],"period":[14],"time.":[16],"Over":[17],"long":[19],"time,":[20],"the":[21,24,36,77,87,95,107,180,194,202],"characteristics":[22],"can":[26],"change":[27],"significantly":[28],"and":[29,48,81,86,133],"frames":[30,135],"are":[31,159,216],"not":[32],"equally":[33],"important,":[34],"underscoring":[35],"need":[37],"for":[38,139,171,184,218],"frame":[39,50,115,126,147,203],"selection.":[40],"In":[41],"this":[42],"paper,":[43],"we":[44],"present":[45],"low-complexity":[47],"effective":[49],"selection":[51],"approach":[52,78,108],"based":[53],"on":[54],"posteriori":[56,91],"signal-to-noise":[57],"ratio":[58],"(SNR)":[59],"weighted":[60],"energy":[61,67],"distance:":[62],"The":[63,144],"use":[64,88],"an":[66],"distance,":[68,75],"instead":[69],"of,":[70],"e.g.,":[71],"standard":[73],"cepstral":[74],"makes":[76],"computationally":[79],"efficient":[80],"enables":[82],"fine":[83],"granularity":[84],"search,":[85],"SNR":[92,142],"weighting":[93],"emphasizes":[94],"reliable":[96],"regions":[97,130],"noisy":[99,177],"signals.":[101,143],"It":[102],"is":[103,109,151,169,182,198,207],"experimentally":[104],"found":[105],"that":[106,158],"able":[110],"to":[111,117,128,136,153,161,209],"assign":[112],"higher":[114],"rate":[116,127,148,197],"fast":[118],"changing":[119],"events":[120],"such":[121],"as":[122],"consonants,":[123],"lower":[125],"steady":[129],"like":[131],"vowels":[132],"no":[134],"silence,":[137],"even":[138],"very":[140],"low":[141],"resulting":[145],"variable":[146],"analysis":[149],"method":[150,181],"applied":[152,208],"three":[154,220],"tasks":[157],"essential":[160],"natural":[162],"interaction":[163],"with":[164],"intelligent":[165],"environments.":[166,178],"First,":[167],"it":[168,206],"used":[170,183],"improving":[172],"recognition":[174,192],"performance":[175],"Second,":[179],"scalable":[185],"source":[186],"coding":[187],"schemes":[188],"distributed":[190],"where":[193],"target":[195],"bit":[196],"met":[199],"by":[200],"adjusting":[201],"rate.":[204],"Third,":[205],"voice":[210],"activity":[211],"detection.":[212],"Very":[213],"encouraging":[214],"results":[215],"obtained":[217],"all":[219],"tasks.":[223]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":16},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}