{"id":"https://openalex.org/W2147749835","doi":"https://doi.org/10.1109/icassp.2012.6288909","title":"Syllable: A self-contained unit to model pronunciation variation","display_name":"Syllable: A self-contained unit to model pronunciation variation","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2147749835","doi":"https://doi.org/10.1109/icassp.2012.6288909","mag":"2147749835"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288909","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288909","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 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/A5071411952","display_name":"Raymond W. M. Ng","orcid":"https://orcid.org/0000-0002-6205-822X"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Raymond W. M. Ng","raw_affiliation_strings":["Graduate School of Information Science and Technology, University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108197272","display_name":"Keikichi Hirose","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keikichi Hirose","raw_affiliation_strings":["Graduate School of Information Science and Technology, University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5071411952"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":2.5689,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.9061854,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"4","issue":null,"first_page":"4457","last_page":"4460"},"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":0.9997000098228455,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9993000030517578,"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/pronunciation","display_name":"Pronunciation","score":0.8343310356140137},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.7558269500732422},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7229130268096924},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.6934492588043213},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6843099594116211},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.6644595265388489},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.4365577697753906},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.41620123386383057},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38662368059158325},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35785433650016785},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.23697549104690552},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.20461136102676392}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.8343310356140137},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.7558269500732422},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7229130268096924},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6934492588043213},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6843099594116211},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.6644595265388489},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.4365577697753906},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.41620123386383057},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38662368059158325},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35785433650016785},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.23697549104690552},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20461136102676392},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2012.6288909","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288909","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.699999988079071,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W40804352","https://openalex.org/W1598371594","https://openalex.org/W1992124213","https://openalex.org/W2095962821","https://openalex.org/W2103219086","https://openalex.org/W2104981903","https://openalex.org/W2116952749","https://openalex.org/W2119491678","https://openalex.org/W2121464381","https://openalex.org/W2167200294","https://openalex.org/W2888226713","https://openalex.org/W3127686677","https://openalex.org/W4236088841","https://openalex.org/W6601648129","https://openalex.org/W6675717942","https://openalex.org/W6753776127"],"related_works":["https://openalex.org/W1667647204","https://openalex.org/W2404647514","https://openalex.org/W4247536566","https://openalex.org/W2183593636","https://openalex.org/W2350724007","https://openalex.org/W2355751417","https://openalex.org/W4241418540","https://openalex.org/W2018477250","https://openalex.org/W3119814709","https://openalex.org/W2061937230"],"abstract_inverted_index":{"In":[0,30],"this":[1,31],"paper,":[2],"we":[3,33],"demonstrate":[4],"the":[5,38,47,80,86,99,108,112,139],"potential":[6],"of":[7,16,42,50,82,89,120,141],"incorporating":[8],"syllable-level":[9],"information":[10],"in":[11,111],"acoustic":[12],"modeling.":[13],"The":[14,123],"unit":[15],"syllable":[17,35,67,71],"is":[18],"not":[19,69],"rigorously":[20],"defined,":[21],"which":[22],"leads":[23,115],"to":[24,97,116,134],"a":[25,51,66,90,117,128],"problem":[26],"for":[27],"its":[28],"use.":[29],"study,":[32],"derive":[34],"structures":[36],"from":[37],"sonorant-band":[39],"intensity":[40],"profile":[41],"speech":[43,54],"signal.":[44],"We":[45,93],"analyze":[46],"error":[48,59],"statistics":[49],"phone-based":[52],"context-dependent":[53],"recognizer":[55],"and":[56,131],"find":[57],"interesting":[58],"patterns.":[60],"Phone":[61],"errors":[62],"mainly":[63],"occur":[64],"inside":[65],"but":[68],"at":[70],"boundaries.":[72],"Pronunciation":[73],"variation":[74,101,137],"can":[75],"thus":[76],"be":[77],"regarded":[78],"as":[79],"replacement":[81],"phonetic":[83],"elements":[84],"within":[85,138],"time":[87],"span":[88],"solitary":[91],"syllable.":[92],"apply":[94],"simple":[95],"rules":[96],"model":[98,135],"pronunciation":[100,136],"phenomenon.":[102],"A":[103],"lexical":[104],"modeling":[105],"approach":[106,133],"modifies":[107],"bi-phone":[109],"transcription":[110],"dictionary.":[113],"It":[114],"significant":[118],"increase":[119],"phone":[121],"correctness.":[122],"results":[124],"shed":[125],"light":[126],"on":[127],"more":[129],"intuitive":[130],"direct":[132],"scope":[140],"syllables.":[142]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
