{"id":"https://openalex.org/W80028043","doi":"https://doi.org/10.21437/interspeech.2006-363","title":"Voice activity detector based on enhanced cumulant of LPC residual and on-line EM algorithm","display_name":"Voice activity detector based on enhanced cumulant of LPC residual and on-line EM algorithm","publication_year":2006,"publication_date":"2006-09-17","ids":{"openalex":"https://openalex.org/W80028043","doi":"https://doi.org/10.21437/interspeech.2006-363","mag":"80028043"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2006-363","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-363","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","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/A5023051838","display_name":"David Cournapeau","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Cournapeau","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111458376","display_name":"Kenji Mase","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kenji Mase","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5108384524","display_name":"Tomoji Toriyama","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomoji Toriyama","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":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"paper 1375","last_page":"Tue3A1O.1"},"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":0.9983999729156494,"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":0.9973999857902527,"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":0.7815545797348022},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6457986235618591},{"id":"https://openalex.org/keywords/autocorrelation","display_name":"Autocorrelation","score":0.6224474310874939},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5845970511436462},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5176361203193665},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5028016567230225},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4702930450439453},{"id":"https://openalex.org/keywords/line","display_name":"Line (geometry)","score":0.45807597041130066},{"id":"https://openalex.org/keywords/pitch-detection-algorithm","display_name":"Pitch detection algorithm","score":0.4298717677593231},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4294961988925934},{"id":"https://openalex.org/keywords/higher-order-statistics","display_name":"Higher-order statistics","score":0.42820608615875244},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4227240979671478},{"id":"https://openalex.org/keywords/jitter","display_name":"Jitter","score":0.4208582937717438},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3688383102416992},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2912942171096802},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.20534783601760864},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11161330342292786}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7815545797348022},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6457986235618591},{"id":"https://openalex.org/C5297727","wikidata":"https://www.wikidata.org/wiki/Q786970","display_name":"Autocorrelation","level":2,"score":0.6224474310874939},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5845970511436462},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5176361203193665},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5028016567230225},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4702930450439453},{"id":"https://openalex.org/C198352243","wikidata":"https://www.wikidata.org/wiki/Q37105","display_name":"Line (geometry)","level":2,"score":0.45807597041130066},{"id":"https://openalex.org/C135622632","wikidata":"https://www.wikidata.org/wiki/Q7198851","display_name":"Pitch detection algorithm","level":3,"score":0.4298717677593231},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4294961988925934},{"id":"https://openalex.org/C2780576426","wikidata":"https://www.wikidata.org/wiki/Q5757980","display_name":"Higher-order statistics","level":4,"score":0.42820608615875244},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4227240979671478},{"id":"https://openalex.org/C134652429","wikidata":"https://www.wikidata.org/wiki/Q1052698","display_name":"Jitter","level":2,"score":0.4208582937717438},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3688383102416992},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2912942171096802},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.20534783601760864},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11161330342292786},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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":1,"locations":[{"id":"doi:10.21437/interspeech.2006-363","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-363","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1560013842","https://openalex.org/W1884359388","https://openalex.org/W2119072456","https://openalex.org/W2120478181","https://openalex.org/W2170644918","https://openalex.org/W2171155529","https://openalex.org/W2250911494","https://openalex.org/W2915280872","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W1537109791","https://openalex.org/W2379831147","https://openalex.org/W2388176952","https://openalex.org/W2039878594","https://openalex.org/W2941168791","https://openalex.org/W2029025464","https://openalex.org/W2066867401","https://openalex.org/W2356656526","https://openalex.org/W2138039466","https://openalex.org/W2107017900"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,14,20,49,64,70,89,96],"problem":[4],"of":[5,16,22,44,48,59,80,91],"segmenting":[6],"audio":[7],"data":[8],"recorded":[9],"with":[10],"embedded":[11],"devices":[12],"for":[13,30,63,117],"purpose":[15],"intelligent":[17],"sensing":[18],"in":[19,34,88],"context":[21,90],"multi-modal":[23],"interactions.":[24],"We":[25],"propose":[26],"a":[27,42,105,111],"real-time":[28,118],"method":[29,72,98],"robust":[31],"speech":[32],"detection":[33,75],"natural,":[35],"noisy":[36],"environments.":[37],"It":[38],"is":[39,99,115],"based":[40,100],"on":[41,101],"fusion":[43],"high":[45],"order":[46],"statistics":[47],"LPC":[50],"residual":[51],"and":[52,54,109],"autocorrelation,":[53],"adopts":[55],"an":[56],"on-line":[57],"version":[58],"Expectation":[60],"Maximization":[61],"algorithm":[62],"classification.":[65],"Experimental":[66],"evaluations":[67],"show":[68],"that":[69],"proposed":[71,97],"provides":[73],"better":[74],"performance":[76],"under":[77],"different":[78],"types":[79],"natural":[81],"noises,":[82],"working":[83],"robustly":[84],"against":[85],"other":[86],"voices":[87],"multi-speaker":[92],"interactive":[93],"situations.":[94],"As":[95],"features":[102],"which":[103],"have":[104],"low":[106],"computational":[107],"cost,":[108],"has":[110],"small":[112],"latency,":[113],"it":[114],"suitable":[116],"tracking":[119],"applications.":[120]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
