{"id":"https://openalex.org/W2115782554","doi":"https://doi.org/10.1109/icassp.2008.4518773","title":"A comparison of phone and grapheme-based spoken term detection","display_name":"A comparison of phone and grapheme-based spoken term detection","publication_year":2008,"publication_date":"2008-03-01","ids":{"openalex":"https://openalex.org/W2115782554","doi":"https://doi.org/10.1109/icassp.2008.4518773","mag":"2115782554"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2008.4518773","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518773","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://era.ed.ac.uk/bitstream/1842/3837/1/icassp08.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100776545","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0002-1286-0644"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dong Wang","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, UK","Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026893328","display_name":"Joe Frankel","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Joe Frankel","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, UK","Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047221036","display_name":"Javier Tejedor","orcid":"https://orcid.org/0000-0001-7699-5620"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Javier Tejedor","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, UK","Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062516688","display_name":"Simon King","orcid":"https://orcid.org/0000-0002-2694-2843"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon King","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, UK","Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":36,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4969","last_page":"4972"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9970999956130981,"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/T12031","display_name":"Speech and dialogue systems","score":0.9943000078201294,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/grapheme","display_name":"Grapheme","score":0.8983708620071411},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8299524188041687},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.7790226936340332},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.7442720532417297},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6313823461532593},{"id":"https://openalex.org/keywords/phonetic-transcription","display_name":"Phonetic transcription","score":0.6066022515296936},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5874675512313843},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5562044382095337},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5057711601257324},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5011718273162842},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.4884147047996521},{"id":"https://openalex.org/keywords/converse","display_name":"Converse","score":0.42634889483451843},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.41645243763923645},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.41499191522598267},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13304945826530457},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07526972889900208}],"concepts":[{"id":"https://openalex.org/C2776779415","wikidata":"https://www.wikidata.org/wiki/Q2545446","display_name":"Grapheme","level":3,"score":0.8983708620071411},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8299524188041687},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.7790226936340332},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.7442720532417297},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6313823461532593},{"id":"https://openalex.org/C2777853878","wikidata":"https://www.wikidata.org/wiki/Q743569","display_name":"Phonetic transcription","level":2,"score":0.6066022515296936},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5874675512313843},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5562044382095337},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5057711601257324},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5011718273162842},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.4884147047996521},{"id":"https://openalex.org/C2776809875","wikidata":"https://www.wikidata.org/wiki/Q1375963","display_name":"Converse","level":2,"score":0.42634889483451843},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41645243763923645},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.41499191522598267},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13304945826530457},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07526972889900208},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2008.4518773","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518773","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:era.ed.ac.uk:1842/3837","is_oa":true,"landing_page_url":"http://hdl.handle.net/1842/3837","pdf_url":"https://era.ed.ac.uk/bitstream/1842/3837/1/icassp08.pdf","source":{"id":"https://openalex.org/S7407055182","display_name":"ERA","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.205.3670","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.205.3670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ir.ii.uam.es/%7Es5t/publications/icassp08.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:era.ed.ac.uk:1842/3837","is_oa":true,"landing_page_url":"http://hdl.handle.net/1842/3837","pdf_url":"https://era.ed.ac.uk/bitstream/1842/3837/1/icassp08.pdf","source":{"id":"https://openalex.org/S7407055182","display_name":"ERA","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},"sustainable_development_goals":[{"score":0.7599999904632568,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322748","display_name":"Vysok\u00e9 U\u010den\u00ed Technick\u00e9 v Brn\u011b","ror":"https://ror.org/03613d656"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2115782554.pdf"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W191801690","https://openalex.org/W1510837697","https://openalex.org/W2056986588","https://openalex.org/W2126897421","https://openalex.org/W2170980774","https://openalex.org/W2405666970","https://openalex.org/W6607752188","https://openalex.org/W6630406810"],"related_works":["https://openalex.org/W2161573742","https://openalex.org/W2050958850","https://openalex.org/W2008308193","https://openalex.org/W3152381020","https://openalex.org/W1565977885","https://openalex.org/W2342534065","https://openalex.org/W2154092232","https://openalex.org/W1987899306","https://openalex.org/W2077460541","https://openalex.org/W2115782554"],"abstract_inverted_index":{"We":[0,67,149],"propose":[1,150],"grapheme-based":[2,78,85,94,134,165],"sub-word":[3],"units":[4],"for":[5,106,155],"spoken":[6],"term":[7],"detection":[8],"(STD).":[9],"Compared":[10],"to":[11],"phones,":[12],"graphemes":[13,35],"have":[14],"a":[15,29,98,114,133,151,181],"number":[16,152],"of":[17,153,158],"potential":[18],"advantages.":[19],"For":[20,80],"out-of-vocabulary":[21,177],"search":[22],"terms,":[23],"phone-":[24,99,110],"based":[25,100,111],"approaches":[26,144],"must":[27],"generate":[28],"pronunciation":[30,43],"using":[31],"letter-to-sound":[32],"rules.":[33],"Using":[34],"obviates":[36],"this":[37,180],"potentially":[38],"error-prone":[39],"hard":[40],"decision,":[41],"shifting":[42],"modelling":[44],"into":[45],"the":[46,50,109,142,171],"statistical":[47],"models":[48,58],"describing":[49],"observation":[51],"space.":[52],"In":[53],"addition,":[54],"long-span":[55],"grapheme":[56,115],"language":[57],"can":[59,167],"be":[60,130,147],"trained":[61],"directly":[62],"from":[63],"large":[64],"text":[65],"corpora.":[66],"present":[68,119],"experiments":[69],"on":[70],"Spanish":[71],"and":[72,77,84,140,161],"English":[73],"data,":[74],"comparing":[75],"phone":[76,83],"STD.":[79],"Spanish,":[81],"where":[82,108],"systems":[86],"give":[87],"similar":[88],"transcription":[89,138],"word":[90],"error":[91],"rates":[92],"(WERs),":[93],"STD":[95,126,166],"significantly":[96],"outperforms":[97,113],"approach.":[101,116,183],"The":[102],"converse":[103],"is":[104],"found":[105],"English,":[107],"system":[112],"However,":[117],"we":[118],"additional":[120],"analysis":[121],"which":[122],"suggests":[123],"that":[124,141,163],"phone-based":[125,169],"performance":[127],"levels":[128],"may":[129,145],"achieved":[131],"by":[132],"approach":[135],"despite":[136],"lower":[137],"accuracy,":[139],"two":[143],"usefully":[146],"combined.":[148],"directions":[154],"future":[156],"development":[157],"these":[159],"ideas,":[160],"suggest":[162],"if":[164],"match":[168],"performance,":[170],"inherent":[172],"flexibility":[173],"in":[174],"dealing":[175],"with":[176],"terms":[178],"makes":[179],"desirable":[182]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
