{"id":"https://openalex.org/W2148487158","doi":"https://doi.org/10.1109/asru.2007.4430079","title":"Factor analysis of acoustic features for streamed hidden Markov modeling","display_name":"Factor analysis of acoustic features for streamed hidden Markov modeling","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2148487158","doi":"https://doi.org/10.1109/asru.2007.4430079","mag":"2148487158"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2007.4430079","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2007.4430079","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","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/A5025826678","display_name":"Chuan-Wei Ting","orcid":null},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chuan-Wei Ting","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061908942","display_name":"Jen\u2010Tzung Chien","orcid":"https://orcid.org/0000-0003-3466-8941"},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jen-Tzung Chien","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan","institution_ids":["https://openalex.org/I91807558"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I91807558"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"30","last_page":"35"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9991000294685364,"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":0.9939000010490417,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.9507529735565186},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7721021771430969},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7119868397712708},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.589633047580719},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5779627561569214},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4923323392868042},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4793075621128082},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4698103070259094},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.45749127864837646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4474503993988037},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.44599300622940063},{"id":"https://openalex.org/keywords/factor","display_name":"Factor (programming language)","score":0.4447647035121918},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.4424268901348114},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.43215465545654297},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.4315006732940674},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.31448525190353394},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2462075650691986},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.24375459551811218},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08227521181106567}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.9507529735565186},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7721021771430969},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7119868397712708},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.589633047580719},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5779627561569214},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4923323392868042},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4793075621128082},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4698103070259094},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.45749127864837646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4474503993988037},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.44599300622940063},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.4447647035121918},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.4424268901348114},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.43215465545654297},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.4315006732940674},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.31448525190353394},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2462075650691986},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.24375459551811218},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08227521181106567},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2007.4430079","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2007.4430079","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W60929302","https://openalex.org/W80444264","https://openalex.org/W175587806","https://openalex.org/W1498305818","https://openalex.org/W1528056001","https://openalex.org/W1560013842","https://openalex.org/W2091024449","https://openalex.org/W2130322773","https://openalex.org/W2137944862","https://openalex.org/W2146608839","https://openalex.org/W2159283619","https://openalex.org/W2160679028","https://openalex.org/W6603255414","https://openalex.org/W6607105664","https://openalex.org/W7028559599"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W4385672897","https://openalex.org/W2373675101","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W2074132948","https://openalex.org/W1510894296","https://openalex.org/W2134386692"],"abstract_inverted_index":{"This":[0,97],"paper":[1],"presents":[2],"a":[3,73,89,116],"new":[4,117],"streamed":[5,75,98],"hidden":[6],"Markov":[7,61,131],"model":[8],"(HMM)":[9],"framework":[10],"for":[11,120,133],"speech":[12,90,122],"recognition.":[13,123],"The":[14,28],"factor":[15,50],"analysis":[16],"(FA)":[17],"is":[18,39,100],"performed":[19],"to":[20,47,63],"discover":[21],"the":[22,34,48,65,81,93,104,108,129,143,145],"common":[23,42],"factors":[24],"of":[25,137],"acoustic":[26],"features.":[27,70],"streaming":[29,109],"regularities":[30],"are":[31,51],"governed":[32],"by":[33,53,153],"correlation":[35],"between":[36],"features,":[37],"which":[38],"inherent":[40],"in":[41,68],"factors.":[43],"Those":[44],"features":[45,87],"corresponding":[46],"same":[49,94],"generated":[52],"identical":[54],"HMM":[55,76,83,99,106],"state.":[56],"Accordingly,":[57],"we":[58,127],"use":[59],"multiple":[60],"chains":[62,132],"represent":[64],"variation":[66],"trends":[67],"cepstral":[69],"We":[71,113],"develop":[72],"FA":[74],"(FASHMM)":[77],"and":[78],"go":[79],"beyond":[80],"conventional":[82],"assuming":[84],"that":[85],"all":[86],"at":[88,155],"frame":[91],"conduct":[92],"state":[95],"emission.":[96],"more":[101],"delicate":[102],"than":[103],"factorial":[105],"where":[107],"was":[110],"empirically":[111],"determined.":[112],"also":[114],"exploit":[115],"decoding":[118],"algorithm":[119],"FASHMM":[121],"In":[124,142],"this":[125],"manner,":[126],"fulfill":[128],"flexible":[130],"an":[134],"input":[135],"sequence":[136],"multivariate":[138],"Gaussian":[139],"mixture":[140],"observations.":[141],"experiments,":[144],"proposed":[146],"method":[147],"can":[148],"reduce":[149],"word":[150],"error":[151],"rate":[152],"36%":[154],"most.":[156]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}