{"id":"https://openalex.org/W1968214459","doi":"https://doi.org/10.1109/iscslp.2010.5684874","title":"Phone boundary refinement using ranking methods","display_name":"Phone boundary refinement using ranking methods","publication_year":2010,"publication_date":"2010-11-01","ids":{"openalex":"https://openalex.org/W1968214459","doi":"https://doi.org/10.1109/iscslp.2010.5684874","mag":"1968214459"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2010.5684874","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2010.5684874","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/A5102235147","display_name":"Hung-Yi Lo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]},{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Hung-Yi Lo","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan","Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102235147"],"corresponding_institution_ids":["https://openalex.org/I16733864","https://openalex.org/I4210098366"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.0691457,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"4","issue":null,"first_page":"488","last_page":"492"},"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/T11309","display_name":"Music and Audio Processing","score":0.9983000159263611,"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/T10860","display_name":"Speech and Audio Processing","score":0.9977999925613403,"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":0.7604167461395264},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.7353579998016357},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.7312777042388916},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.7267020344734192},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.63214111328125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6294776797294617},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6072435975074768},{"id":"https://openalex.org/keywords/decision-boundary","display_name":"Decision boundary","score":0.5893411040306091},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5713614225387573},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.5548527836799622},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.5091428160667419},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.4942303001880646},{"id":"https://openalex.org/keywords/ranking-svm","display_name":"Ranking SVM","score":0.44705477356910706},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43549588322639465},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.41403627395629883},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3884093761444092},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33518466353416443},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13330510258674622}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7604167461395264},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.7353579998016357},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.7312777042388916},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.7267020344734192},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.63214111328125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6294776797294617},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6072435975074768},{"id":"https://openalex.org/C42023084","wikidata":"https://www.wikidata.org/wiki/Q5249231","display_name":"Decision boundary","level":3,"score":0.5893411040306091},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5713614225387573},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.5548527836799622},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.5091428160667419},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.4942303001880646},{"id":"https://openalex.org/C124975894","wikidata":"https://www.wikidata.org/wiki/Q7293290","display_name":"Ranking SVM","level":3,"score":0.44705477356910706},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43549588322639465},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.41403627395629883},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3884093761444092},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33518466353416443},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13330510258674622},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2010.5684874","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2010.5684874","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":[{"score":0.7799999713897705,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321040","display_name":"National Science Council","ror":"https://ror.org/02kv4zf79"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W172543864","https://openalex.org/W182487737","https://openalex.org/W1552767446","https://openalex.org/W1761091820","https://openalex.org/W2047221353","https://openalex.org/W2059026503","https://openalex.org/W2106221537","https://openalex.org/W2118585731","https://openalex.org/W2124254786","https://openalex.org/W2149999905","https://openalex.org/W2153635508","https://openalex.org/W2169711598","https://openalex.org/W3120421331","https://openalex.org/W4285719527","https://openalex.org/W6606993375","https://openalex.org/W6607467561","https://openalex.org/W6632992187","https://openalex.org/W6677656871","https://openalex.org/W6678606345"],"related_works":["https://openalex.org/W2136652457","https://openalex.org/W2169849734","https://openalex.org/W2116722627","https://openalex.org/W2129150969","https://openalex.org/W2236912844","https://openalex.org/W1975869217","https://openalex.org/W2401728283","https://openalex.org/W2383829109","https://openalex.org/W2379938888","https://openalex.org/W2386035178"],"abstract_inverted_index":{"The":[0,12,103,121,133],"HMM/SVM-based":[1],"two-stage":[2,13],"framework":[3],"has":[4],"been":[5],"widely":[6],"used":[7],"for":[8,40],"automatic":[9],"phone":[10,43],"alignment.":[11,29],"method":[14,116],"uses":[15],"SVM":[16,98],"classifiers":[17],"to":[18,80],"refine":[19,81],"the":[20,25,37,42,46,53,62,67,82,108,113,118],"hypothesized":[21,83],"boundaries":[22],"given":[23],"by":[24,90],"HMM-based":[26],"Viterbi":[27],"forced":[28],"However,":[30],"there":[31],"are":[32,101],"two":[33],"drawbacks":[34],"in":[35],"using":[36,77,91],"classification":[38,63,119],"model":[39,64],"detecting":[41],"boundaries.":[44,84],"First,":[45],"training":[47,69],"data":[48],"contains":[49],"only":[50],"information":[51],"about":[52],"boundary":[54,135],"and":[55,93,99],"far":[56],"away":[57],"non-boundary":[58],"signal":[59],"characteristics.":[60],"Second,":[61],"suffers":[65],"from":[66],"class-imbalanced":[68],"problem.":[70],"To":[71],"overcome":[72],"these":[73],"drawbacks,":[74],"we":[75],"propose":[76],"ranking":[78,115],"methods":[79],"We":[85],"train":[86],"multiple":[87],"phone-transition-dependent":[88],"rankers":[89],"K-means-based":[92],"decision-tree-based":[94],"clustering.":[95],"Both":[96],"Ranking":[97],"RankBoost":[100],"evaluated.":[102],"results":[104],"of":[105,130],"experiments":[106],"on":[107],"TIMIT":[109],"corpus":[110],"demonstrate":[111],"that":[112],"proposed":[114],"outperforms":[117],"method.":[120],"best":[122],"accuracy":[123],"achieved":[124],"is":[125,137],"84.20%":[126],"within":[127],"a":[128],"tolerance":[129],"10":[131],"ms.":[132,139],"mean":[134],"distance":[136],"6.66":[138]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}