{"id":"https://openalex.org/W2408056802","doi":"https://doi.org/10.21437/interspeech.2011-630","title":"Frame-level vocal effort likelihood space modeling for improved whisper-island detection","display_name":"Frame-level vocal effort likelihood space modeling for improved whisper-island detection","publication_year":2011,"publication_date":"2011-08-27","ids":{"openalex":"https://openalex.org/W2408056802","doi":"https://doi.org/10.21437/interspeech.2011-630","mag":"2408056802"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2011-630","doi":"https://doi.org/10.21437/interspeech.2011-630","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-630","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"},"volume":null,"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/A5100458226","display_name":"Chi Zhang","orcid":"https://orcid.org/0000-0003-0865-5215","observed_orcids":["https://orcid.org/0000-0003-0865-5215"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chi Zhang","raw_affiliation_strings":["University of Texas at Dallas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929","observed_orcids":["https://orcid.org/0000-0003-1382-9929"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"John H. L. Hansen","raw_affiliation_strings":["Electrical Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical Engineering","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2504,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53482677,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2421","last_page":"2424"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8916000127792358,"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":0.8916000127792358,"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":0.10440000146627426,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.0013000000035390258,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/vocal-effort","display_name":"vocal effort","score":0.875},{"id":"https://openalex.org/keywords/gaussian-mixture-model","display_name":"Gaussian mixture model","score":0.878000020980835},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"dimensionality reduction","score":0.6269999742507935},{"id":"https://openalex.org/keywords/speech-segmentation","display_name":"speech segmentation","score":0.5260000228881836},{"id":"https://openalex.org/keywords/computational-cost-reduction","display_name":"computational complexity reduction","score":0.6790000200271606}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7644201517105103},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6880307197570801},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6327228546142578},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6163287162780762},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5274743437767029},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5263465642929077},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.5084537267684937},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.49752381443977356},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47436603903770447},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4732012450695038},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.45264768600463867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4446754455566406},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.4347797632217407},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3145267367362976},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2011-630","doi":"https://doi.org/10.21437/interspeech.2011-630","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-630","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W37326695","https://openalex.org/W41355022","https://openalex.org/W48525746","https://openalex.org/W177407077","https://openalex.org/W1935041840","https://openalex.org/W2022047569","https://openalex.org/W2074936909","https://openalex.org/W2104353650","https://openalex.org/W2145404233","https://openalex.org/W2398145559","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2023697902","https://openalex.org/W41355022","https://openalex.org/W2155517073","https://openalex.org/W2074936909","https://openalex.org/W109284678","https://openalex.org/W1981529741","https://openalex.org/W48525746","https://openalex.org/W1536024295","https://openalex.org/W163913193","https://openalex.org/W2055589033"],"abstract_inverted_index":{"In":[0],"this":[1],"study,":[2],"a":[3,30,46,67,116,170],"frame-based":[4],"vocal":[5,74],"effort":[6,75],"likelihood":[7],"space":[8],"modeling":[9],"framework":[10,88,110],"for":[11,35,57,73,104,153,174],"improved":[12],"whisper-island":[13,58,105],"detection":[14,106,132,144,172,183],"within":[15,66],"normally":[16],"phonated":[17],"audio":[18],"streams":[19],"is":[20,25,41,64,125,151],"proposed.":[21],"The":[22,60,122],"proposed":[23,48,87,109,123,148,176],"method":[24,95],"based":[26],"on":[27],"first":[28],"training":[29],"traditional":[31],"Gaussian":[32],"mixture":[33],"model":[34],"whisper":[36,164],"and":[37,113],"neutral":[38],"speech,":[39],"which":[40,150,178],"then":[42],"employed":[43],"to":[44,127,193],"extract":[45],"newly":[47],"discriminative":[49],"feature":[50,62,84],"set":[51,63],"entitled":[52],"Vocal":[53,197,200],"Effort":[54,198],"Likelihood":[55],"(VEL),":[56],"detection.":[59,78],"VEL":[61,82],"integrated":[65],"BIC/T":[68],"2":[69],"-BIC":[70],"segmentation":[71],"scheme":[72],"change":[76],"point(VECP)":[77],"With":[79],"the":[80,86,100,108,134,175,180,191],"dimension-reduced":[81],"2-D":[83],"set,":[85],"has":[89],"reduced":[90],"computational":[91,187],"costs":[92,188],"versus":[93],"prior":[94],"[1].":[96,121],"Experimental":[97],"results":[98],"using":[99,107,147],"UT-VocalEffort":[101],"II":[102],"corpus":[103],"are":[111],"presented":[112],"compared":[114],"with":[115,133,185],"previous":[117],"algorithm":[118,124],"introduced":[119],"in":[120,130,156,190],"shown":[126],"improve":[128],"performance":[129,155,168,184],"VECP":[131],"lowest":[135,186],"MultiError":[136],"Score(MES)":[137],"of":[138],"6.33.":[139],"Furthermore,":[140],"very":[141],"accurate":[142],"whisperisland":[143,182],"was":[145],"obtained":[146],"algorithm,":[149,177],"useful":[152],"sustained":[154],"speech":[157],"systems":[158],"(ASR,":[159],"Speaker-ID,":[160],"etc.)which":[161],"might":[162],"experience":[163],"speech.":[165],"Finally,":[166],"experimental":[167],"achieves":[169],"100%":[171],"rate":[173],"represents":[179],"best":[181],"available":[189],"literature":[192],"date.":[194],"Index":[195],"Terms:":[196],"Likelihood,":[199],"Effort,":[201],"WhisperIsland":[202],"Detection,":[203],"GMM":[204],"Classifier":[205]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2026-10-06T10:28:23.643775","created_date":"2016-06-24T00:00:00"}