{"id":"https://openalex.org/W2101965210","doi":"https://doi.org/10.1109/icassp.2011.5947452","title":"Eigentriphones: A basis for context-dependent acoustic modeling","display_name":"Eigentriphones: A basis for context-dependent acoustic modeling","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2101965210","doi":"https://doi.org/10.1109/icassp.2011.5947452","mag":"2101965210"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947452","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947452","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5038062913","display_name":"Tom Ko","orcid":"https://orcid.org/0000-0002-5324-8961"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Tom Ko","raw_affiliation_strings":["Department of Computer Science and Engineering, Hong Kong University of Science & Technology (HKUST), Clear Water Bay, China","Department of Computer Science and Engineering, the Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Hong Kong University of Science & Technology (HKUST), Clear Water Bay, China","institution_ids":["https://openalex.org/I889458895","https://openalex.org/I200769079"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, the Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059141717","display_name":"Brian Mak","orcid":"https://orcid.org/0000-0001-6787-5555"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Brian Mak","raw_affiliation_strings":["Department of Computer Science and Engineering, Hong Kong University of Science & Technology (HKUST), Clear Water Bay, China","Department of Computer Science and Engineering, the Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Hong Kong University of Science & Technology (HKUST), Clear Water Bay, China","institution_ids":["https://openalex.org/I889458895","https://openalex.org/I200769079"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, the Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5038062913"],"corresponding_institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":2.993,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.91841735,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"3","issue":null,"first_page":"4892","last_page":"4895"},"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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9995999932289124,"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":0.7960027456283569},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7001336812973022},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.643268883228302},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6129074096679688},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5744092464447021},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.5462103486061096},{"id":"https://openalex.org/keywords/tying","display_name":"Tying","score":0.47242867946624756},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.46836957335472107},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4665944576263428},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4566452205181122},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4432280659675598},{"id":"https://openalex.org/keywords/basis","display_name":"Basis (linear algebra)","score":0.42763805389404297},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33934104442596436},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09960144758224487}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7960027456283569},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7001336812973022},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.643268883228302},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6129074096679688},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5744092464447021},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.5462103486061096},{"id":"https://openalex.org/C2780938662","wikidata":"https://www.wikidata.org/wiki/Q973710","display_name":"Tying","level":2,"score":0.47242867946624756},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.46836957335472107},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4665944576263428},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4566452205181122},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4432280659675598},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.42763805389404297},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33934104442596436},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09960144758224487},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2011.5947452","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947452","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-39770","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-39770","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7400000095367432,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W107086600","https://openalex.org/W206545267","https://openalex.org/W943204654","https://openalex.org/W1805340023","https://openalex.org/W2116952749","https://openalex.org/W2121178390","https://openalex.org/W2142873456","https://openalex.org/W2147794814","https://openalex.org/W2151402979","https://openalex.org/W2165108269","https://openalex.org/W4236088841","https://openalex.org/W6608450475"],"related_works":["https://openalex.org/W2998037107","https://openalex.org/W1597439699","https://openalex.org/W1569871744","https://openalex.org/W2016024526","https://openalex.org/W2379437105","https://openalex.org/W3139928442","https://openalex.org/W1567336638","https://openalex.org/W954011496","https://openalex.org/W3124892642","https://openalex.org/W2145850538"],"abstract_inverted_index":{"In":[0,23,41,75],"context-dependent":[1],"acoustic":[2,121],"modeling,":[3],"it":[4],"is":[5,30],"important":[6],"to":[7,37,57],"strike":[8],"a":[9,59,67,93,119,164],"balance":[10],"between":[11],"detailed":[12],"modeling":[13,122],"and":[14,50,88,148],"data":[15],"sufficiency":[16],"for":[17,124],"robust":[18],"estimation":[19],"of":[20,32,66,70,82,113],"model":[21,89],"parameters.":[22],"the":[24,33,39,53,80,86,96,100,103,111,114,129,140,157,181],"past,":[25],"parameter":[26],"sharing":[27],"or":[28,61,73],"tying":[29,134,174],"one":[31],"most":[34],"common":[35,182],"techniques":[36],"solve":[38],"problem.":[40],"recent":[42],"years,":[43],"another":[44,107],"technique":[45],"which":[46],"may":[47,150,175],"be":[48,151],"loosely":[49],"collectively":[51],"called":[52],"subspace":[54],"approach":[55],"tries":[56],"express":[58],"phonetic":[60],"sub-phonetic":[62],"unit":[63],"in":[64,95,102],"terms":[65],"small":[68],"set":[69],"canonical":[71],"vectors":[72],"units.":[74],"this":[76],"paper,":[77],"we":[78,109],"investigate":[79,110],"development":[81],"an":[83],"eigenbasis":[84],"over":[85],"triphones":[87,126,132,141],"each":[90,146],"triphone":[91,165],"as":[92,118],"point":[94],"basis.":[97],"We":[98],"call":[99],"eigenvectors":[101],"basis":[104],"eigentriphones.":[105],"From":[106],"perspective,":[108],"use":[112],"eigenvoice":[115],"adaptation":[116],"method":[117,123],"general":[120],"training":[125],"-":[127],"especially":[128],"less":[130],"frequent":[131],"without":[133,172],"their":[135],"states":[136],"so":[137],"that":[138,163],"all":[139],"are":[142],"really":[143],"distinct":[144],"from":[145],"other":[147],"thus":[149],"more":[152],"discriminative.":[153],"Experimental":[154],"evaluation":[155],"on":[156],"5K-vocabulary":[158],"HUB2":[159],"recognition":[160],"task":[161],"shows":[162],"HMM":[166],"system":[167],"trained":[168],"using":[169],"only":[170],"eigentriphones":[171],"state":[173],"achieve":[176],"slightly":[177],"better":[178],"performance":[179],"than":[180],"tied-state":[183],"triphones.":[184]},"counts_by_year":[{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}