{"id":"https://openalex.org/W2117541506","doi":"https://doi.org/10.1109/icassp.2009.4960617","title":"Revisiting graphemes with increasing amounts of data","display_name":"Revisiting graphemes with increasing amounts of data","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2117541506","doi":"https://doi.org/10.1109/icassp.2009.4960617","mag":"2117541506"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960617","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960617","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5113807382","display_name":"Yun-Hsuan Sung","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yun-Hsuan Sung","raw_affiliation_strings":["Department of EE, University of Stanford, Stanford, CA, USA","Google, Inc., Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of EE, University of Stanford, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Google, Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061980970","display_name":"T. A. Hughes","orcid":"https://orcid.org/0000-0003-3481-0397"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thad Hughes","raw_affiliation_strings":["Google, Inc., Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110711540","display_name":"Fran\u00e7oise Beaufays","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Francoise Beaufays","raw_affiliation_strings":["Google, Inc., Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001487094","display_name":"Brian Strope","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Strope","raw_affiliation_strings":["Google, Inc., Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4449","last_page":"4452"},"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":0.9993000030517578,"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":0.9983000159263611,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/grapheme","display_name":"Grapheme","score":0.960502028465271},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.850568413734436},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8202196955680847},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.666278600692749},{"id":"https://openalex.org/keywords/coda","display_name":"Coda","score":0.6591054201126099},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5577095746994019},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5420343279838562},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5286750197410583},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5183959603309631},{"id":"https://openalex.org/keywords/orthography","display_name":"Orthography","score":0.5063101053237915},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5046166181564331},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4711032509803772},{"id":"https://openalex.org/keywords/ranging","display_name":"Ranging","score":0.44695860147476196},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1533169150352478}],"concepts":[{"id":"https://openalex.org/C2776779415","wikidata":"https://www.wikidata.org/wiki/Q2545446","display_name":"Grapheme","level":3,"score":0.960502028465271},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.850568413734436},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8202196955680847},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.666278600692749},{"id":"https://openalex.org/C3962253","wikidata":"https://www.wikidata.org/wiki/Q852466","display_name":"Coda","level":2,"score":0.6591054201126099},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5577095746994019},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5420343279838562},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5286750197410583},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5183959603309631},{"id":"https://openalex.org/C150670947","wikidata":"https://www.wikidata.org/wiki/Q43091","display_name":"Orthography","level":3,"score":0.5063101053237915},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5046166181564331},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4711032509803772},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.44695860147476196},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1533169150352478},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C165205528","wikidata":"https://www.wikidata.org/wiki/Q83371","display_name":"Seismology","level":1,"score":0.0},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.0},{"id":"https://openalex.org/C30080830","wikidata":"https://www.wikidata.org/wiki/Q169917","display_name":"Graphene","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","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/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.2009.4960617","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960617","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.225.235","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.225.235","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.stanford.edu/%7Eyhsung/papers/icassp2009grapheme.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W74294255","https://openalex.org/W83248749","https://openalex.org/W1510837697","https://openalex.org/W1896748021","https://openalex.org/W2106554350","https://openalex.org/W2121464381","https://openalex.org/W2154341695","https://openalex.org/W2158286329","https://openalex.org/W2166799778","https://openalex.org/W2167200294","https://openalex.org/W3150637114","https://openalex.org/W6630406810","https://openalex.org/W6683703931"],"related_works":["https://openalex.org/W170464811","https://openalex.org/W264981030","https://openalex.org/W2047487744","https://openalex.org/W4200164668","https://openalex.org/W2073818295","https://openalex.org/W2080578089","https://openalex.org/W2327730116","https://openalex.org/W2027274657","https://openalex.org/W2179005426","https://openalex.org/W3029982911"],"abstract_inverted_index":{"Letter":[0],"units,":[1,20],"or":[2,140],"graphemes,":[3],"have":[4,40],"been":[5],"reported":[6,45],"in":[7,23],"the":[8,16,93,129,137,142,146],"literature":[9],"as":[10],"a":[11,27,65],"surprisingly":[12],"effective":[13],"substitute":[14],"to":[15,64,79,84,108],"more":[17,81],"traditional":[18],"phoneme":[19,100,143],"at":[21],"least":[22],"languages":[24],"that":[25,128],"enjoy":[26],"strong":[28],"correspondence":[29],"between":[30],"pronunciation":[31,53],"and":[32,99,123],"orthography.":[33],"For":[34],"English":[35],"however,":[36],"where":[37],"letter":[38],"symbols":[39],"less":[41],"acoustic":[42,69,77],"consistency,":[43],"previously":[44],"results":[46],"fell":[47],"short":[48],"of":[49,68,95,97,111],"systems":[50,101,131],"using":[51,120],"highly-tuned":[52],"lexicons.":[54],"Grapheme":[55],"units":[56],"simplify":[57],"system":[58],"design,":[59],"but":[60],"since":[61],"graphemes":[62],"map":[63],"wider":[66],"set":[67],"realizations":[70],"than":[71],"phonemes,":[72],"we":[73,91],"should":[74],"expect":[75],"grapheme-based":[76],"models":[78],"require":[80],"training":[82,148],"data":[83],"capture":[85],"these":[86],"variations.":[87],"In":[88],"this":[89],"paper,":[90],"compare":[92],"rate":[94],"improvement":[96],"grapheme":[98,116,130],"trained":[102],"with":[103,145],"datasets":[104],"ranging":[105],"from":[106],"450":[107],"1200":[109],"hours":[110],"speech.":[112],"We":[113,126],"consider":[114],"various":[115],"unit":[117],"configurations,":[118],"including":[119],"letter-specific,":[121],"onset,":[122],"coda":[124],"units.":[125],"show":[127],"improve":[132],"faster":[133],"and,":[134],"depending":[135],"on":[136],"lexicon,":[138],"reach":[139],"surpass":[141],"baselines":[144],"largest":[147],"set.":[149]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}