{"id":"https://openalex.org/W1982486113","doi":"https://doi.org/10.1109/iscslp.2010.5684481","title":"Automatic voice onset time estimation of stops in continuous speech","display_name":"Automatic voice onset time estimation of stops in continuous speech","publication_year":2010,"publication_date":"2010-11-01","ids":{"openalex":"https://openalex.org/W1982486113","doi":"https://doi.org/10.1109/iscslp.2010.5684481","mag":"1982486113"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2010.5684481","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2010.5684481","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 7th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-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/A5035641569","display_name":"Chi-Yueh Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chi-Yueh Lin","raw_affiliation_strings":["Department of Electrical Engineering, National Tsing Hua University, Taiwan","Department of Electrical Engineering; National Tsing Hua University; Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Tsing Hua University, Taiwan","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"Department of Electrical Engineering; National Tsing Hua University; Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055326144","display_name":"Hsiao-Chuan Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsiao-Chuan Wang","raw_affiliation_strings":["Department of Electrical Engineering, National Tsing Hua University, Taiwan","Department of Electrical Engineering; National Tsing Hua University; Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Tsing Hua University, Taiwan","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"Department of Electrical Engineering; National Tsing Hua University; Taiwan","institution_ids":["https://openalex.org/I25846049"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5035641569"],"corresponding_institution_ids":["https://openalex.org/I25846049"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.0823601,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"136","issue":null,"first_page":"471","last_page":"476"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10860","display_name":"Speech and Audio Processing","score":0.9987000226974487,"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/T11309","display_name":"Music and Audio Processing","score":0.9944999814033508,"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":0.821567177772522},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7630270719528198},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.658345639705658},{"id":"https://openalex.org/keywords/voice-onset-time","display_name":"Voice-onset time","score":0.6446549296379089},{"id":"https://openalex.org/keywords/stop-consonant","display_name":"Stop consonant","score":0.644062876701355},{"id":"https://openalex.org/keywords/voice","display_name":"Voice","score":0.6416199803352356},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.6334038376808167},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6322548985481262},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5966174602508545},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5153831243515015},{"id":"https://openalex.org/keywords/interval","display_name":"Interval (graph theory)","score":0.4989290237426758},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4932224154472351},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4801185131072998},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4112018346786499},{"id":"https://openalex.org/keywords/consonant","display_name":"Consonant","score":0.4081205725669861},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10271215438842773},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06018480658531189}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.821567177772522},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7630270719528198},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.658345639705658},{"id":"https://openalex.org/C89051679","wikidata":"https://www.wikidata.org/wiki/Q627770","display_name":"Voice-onset time","level":3,"score":0.6446549296379089},{"id":"https://openalex.org/C2776893716","wikidata":"https://www.wikidata.org/wiki/Q51597","display_name":"Stop consonant","level":4,"score":0.644062876701355},{"id":"https://openalex.org/C552089266","wikidata":"https://www.wikidata.org/wiki/Q494510","display_name":"Voice","level":2,"score":0.6416199803352356},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6334038376808167},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6322548985481262},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5966174602508545},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5153831243515015},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.4989290237426758},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4932224154472351},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4801185131072998},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4112018346786499},{"id":"https://openalex.org/C2778203577","wikidata":"https://www.wikidata.org/wiki/Q38035","display_name":"Consonant","level":3,"score":0.4081205725669861},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10271215438842773},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06018480658531189},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2010.5684481","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2010.5684481","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 7th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W91681889","https://openalex.org/W93767964","https://openalex.org/W174951031","https://openalex.org/W1581809089","https://openalex.org/W2041282815","https://openalex.org/W2042165210","https://openalex.org/W2077804127","https://openalex.org/W2089366861","https://openalex.org/W2111477235","https://openalex.org/W2138816860","https://openalex.org/W2911964244","https://openalex.org/W3127686677","https://openalex.org/W4247128285","https://openalex.org/W6603794975","https://openalex.org/W6607188436","https://openalex.org/W6789826613"],"related_works":["https://openalex.org/W2033051549","https://openalex.org/W2041494451","https://openalex.org/W2164875251","https://openalex.org/W2989621856","https://openalex.org/W2068841577","https://openalex.org/W2486090945","https://openalex.org/W2466341264","https://openalex.org/W2037728892","https://openalex.org/W2991402433","https://openalex.org/W2075252927"],"abstract_inverted_index":{"To":[0],"annotate":[1],"voice":[2],"onset":[3,49,64,103,111],"time":[4,80],"(VOT)":[5],"of":[6,74,95,118,147],"stop":[7,60,69,91],"consonants":[8],"in":[9,100,130],"a":[10,16,26,44,55,115],"speech":[11],"database,":[12,132],"manually":[13],"labeling":[14],"is":[15,85,106],"feasible":[17],"but":[18],"time-consuming":[19],"and":[20,43,62,76,137,158],"tedious":[21],"task.":[22],"This":[23],"paper":[24],"proposed":[25,97,122],"fully-automatic":[27],"VOT":[28,88],"estimation":[29],"method":[30,36,98,123],"to":[31,58,108],"alleviate":[32],"this":[33],"burden.":[34],"The":[35,51,93,121,141],"relies":[37],"on":[38,126],"an":[39],"HMM-based":[40],"phone":[41,52],"recognizer":[42,53],"random":[45],"forest":[46],"(RF)":[47],"based":[48],"detector.":[50],"performs":[54],"forced":[56],"alignment":[57],"locate":[59],"consonants,":[61],"the":[63,72,79,86,96,101,127,148,152],"detector":[65],"searches":[66],"each":[67],"aligned":[68],"segment":[70],"for":[71,89],"onsets":[73,84],"burst":[75],"voicing.":[77],"Then":[78],"interval":[81],"between":[82],"these":[83],"estimated":[87],"that":[90,145],"consonant.":[92],"merit":[94],"lies":[99],"RF-based":[102],"detector,":[104],"which":[105,133],"able":[107],"provide":[109],"accurate":[110],"detection":[112],"with":[113],"only":[114],"small":[116],"amount":[117],"training":[119],"data.":[120],"was":[124],"evaluated":[125],"testing":[128],"set":[129],"TIMIT":[131],"includes":[134],"2,344":[135],"word-initial":[136],"1,440":[138],"word-medial":[139],"stops.":[140],"experimental":[142],"results":[143],"revealed":[144],"81.2%":[146],"estimations":[149],"deviate":[150],"from":[151],"reference":[153],"values":[154],"within":[155,160],"10":[156],"ms,":[157],"95.7%":[159],"20":[161],"ms.":[162]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-02T13:48:15.688549","created_date":"2025-10-10T00:00:00"}
