{"id":"https://openalex.org/W86842594","doi":"https://doi.org/10.21437/icslp.2002-40","title":"A hybrid HMM/traps model for robust voice activity detection","display_name":"A hybrid HMM/traps model for robust voice activity detection","publication_year":2002,"publication_date":"2002-09-16","ids":{"openalex":"https://openalex.org/W86842594","doi":"https://doi.org/10.21437/icslp.2002-40","mag":"86842594"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.2002-40","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2002-40","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th International Conference on Spoken Language Processing (ICSLP 2002)","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/A5003725957","display_name":"Brian Kingsbury","orcid":"https://orcid.org/0000-0002-1343-6837"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brian Kingsbury","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107254650","display_name":"Pratibha Jain","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pratibha Jain","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5033711275","display_name":"Andr\u00e9 Adami","orcid":"https://orcid.org/0000-0001-8105-7698"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andre Adami","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":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1073","last_page":"1076"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8319456577301025},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7503324747085571},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7053400278091431},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5637030601501465},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5488166213035583},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5470763444900513},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.5211727023124695},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5085569620132446},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4724191427230835},{"id":"https://openalex.org/keywords/voice","display_name":"Voice","score":0.45659953355789185},{"id":"https://openalex.org/keywords/viterbi-decoder","display_name":"Viterbi decoder","score":0.44426289200782776},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.43992358446121216},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4165414571762085},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4134475588798523},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09715983271598816},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.09616795182228088}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8319456577301025},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7503324747085571},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7053400278091431},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5637030601501465},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5488166213035583},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5470763444900513},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.5211727023124695},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5085569620132446},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4724191427230835},{"id":"https://openalex.org/C552089266","wikidata":"https://www.wikidata.org/wiki/Q494510","display_name":"Voice","level":2,"score":0.45659953355789185},{"id":"https://openalex.org/C117379686","wikidata":"https://www.wikidata.org/wiki/Q6996459","display_name":"Viterbi decoder","level":3,"score":0.44426289200782776},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.43992358446121216},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4165414571762085},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4134475588798523},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09715983271598816},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.09616795182228088},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/icslp.2002-40","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2002-40","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th International Conference on Spoken Language Processing (ICSLP 2002)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W190289757","https://openalex.org/W1553004968","https://openalex.org/W1596681162","https://openalex.org/W1599512239","https://openalex.org/W1932968309","https://openalex.org/W2002342963","https://openalex.org/W2090861223","https://openalex.org/W2104663520","https://openalex.org/W2105613081","https://openalex.org/W2106420626","https://openalex.org/W2124629003","https://openalex.org/W2132214951","https://openalex.org/W2149053750","https://openalex.org/W2160339736","https://openalex.org/W2167763959","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2102309991","https://openalex.org/W1795315578","https://openalex.org/W2373954783","https://openalex.org/W2535886977","https://openalex.org/W2133857928","https://openalex.org/W2143297499","https://openalex.org/W2356694334","https://openalex.org/W2991144886","https://openalex.org/W2790444905","https://openalex.org/W1843778016"],"abstract_inverted_index":{"We":[0],"present":[1],"three":[2],"voice":[3],"activity":[4],"detection":[5],"(VAD)":[6],"algorithms":[7],"that":[8,43,103,110],"are":[9],"suitable":[10],"for":[11],"the":[12,32,67,80,83,97,113,118,128],"off-line":[13],"processing":[14,81],"of":[15,50,82],"noisy":[16],"speech":[17,27,68],"and":[18,47],"compare":[19],"their":[20],"performance":[21],"on":[22,62,117,127],"SPINE-2":[23],"evaluation":[24],"data":[25],"using":[26,70],"recognition":[28,126],"error":[29,152],"rate":[30],"as":[31,53],"quality":[33],"metric.":[34],"One":[35,86],"VAD":[36,59,87],"system":[37,88,102],"is":[38,99,122,137],"a":[39,48,71,100,105,141,147],"simple":[40],"HMM-based":[41],"segmenter":[42],"uses":[44,89,104],"normalized":[45],"log-energy":[46],"degree":[49],"voicing":[51],"measure":[52],"raw":[54],"features.":[55],"The":[56],"other":[57,98,129],"two":[58,130],"systems":[60],"focus":[61],"frequency-localized":[63],"temporal":[64],"information":[65],"in":[66,79,112],"signal":[69],"TempoRAl":[72],"PatternS":[73],"(TRAPS)":[74],"classifier.":[75],"They":[76],"differ":[77],"only":[78],"TRAPS":[84],"output.":[85],"median":[90],"filtering":[91],"to":[92,109,146],"generate":[93],"segment":[94],"hypotheses,":[95],"while":[96],"hybrid":[101,119],"Viterbi":[106],"search":[107],"identical":[108],"used":[111],"HMM":[114],"segmenter.":[115],"Recognition":[116],"HMM/TRAPS":[120],"segmentation":[121],"more":[123],"accurate":[124],"than":[125],"segmentations":[131],"by":[132],"1%":[133],"absolute.":[134],"This":[135],"difference":[136],"statistically":[138],"significant":[139],"at":[140],"99%":[142],"confidence":[143],"level":[144],"according":[145],"matched":[148],"pairs":[149],"sentence-segment":[150],"word":[151],"test.":[153]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}