{"id":"https://openalex.org/W2103085228","doi":"https://doi.org/10.1017/s1351324914000175","title":"The Kestrel TTS text normalization system","display_name":"The Kestrel TTS text normalization system","publication_year":2014,"publication_date":"2014-12-12","ids":{"openalex":"https://openalex.org/W2103085228","doi":"https://doi.org/10.1017/s1351324914000175","mag":"2103085228"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324914000175","doi":"https://doi.org/10.1017/s1351324914000175","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324914000175","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-b","jufo-3","poland-140","vabb-shw"],"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},"volume":null,"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/A5080511613","display_name":"PETER EBDEN","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210113297","display_name":"Google (United Kingdom)","ror":"https://ror.org/024bc3e07","country_code":"GB","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210113297","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"PETER EBDEN","raw_affiliation_strings":["Google, Inc (now at Thought Machine), London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc (now at Thought Machine), London, UK","institution_ids":["https://openalex.org/I4210113297"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063612469","display_name":"Richard Sproat","orcid":"https://orcid.org/0000-0002-9040-5196","observed_orcids":["https://orcid.org/0000-0002-9040-5196"]},"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":"RICHARD SPROAT","raw_affiliation_strings":["Google, Inc, New York, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc, New York, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3201,"has_fulltext":false,"cited_by_count":70,"citation_normalized_percentile":{"value":0.92392913,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"21","issue":"3","first_page":"333","last_page":"353"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9922000169754028,"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":0.9922000169754028,"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":0.003700000001117587,"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":0.003700000001117587,"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/kestrel","display_name":"kestrel","score":0.7039999961853027},{"id":"https://openalex.org/keywords/text-normalization","display_name":"text normalization","score":0.8339999914169312},{"id":"https://openalex.org/keywords/text-to-speech","display_name":"text-to-speech","score":0.9810000061988831},{"id":"https://openalex.org/keywords/weighted-finite-state-transducers","display_name":"weighted finite-state transducers","score":0.9919999837875366},{"id":"https://openalex.org/keywords/protocol-buffers","display_name":"Protocol Buffers","score":0.7459999918937683},{"id":"https://openalex.org/keywords/tokenization","display_name":"tokenization","score":0.6079999804496765},{"id":"https://openalex.org/keywords/verbalization","display_name":"verbalization","score":0.7850000262260437},{"id":"https://openalex.org/keywords/multilingual-speech-synthesis","display_name":"multilingual speech synthesis","score":0.7260000109672546}],"concepts":[{"id":"https://openalex.org/C2780750384","wikidata":"https://www.wikidata.org/wiki/Q2488588","display_name":"Kestrel","level":3,"score":0.9249755144119263},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8188261985778809},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7636194229125977},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6212487816810608},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.6106153726577759},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5403767824172974},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42979347705841064},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.4271796941757202},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C188382862","wikidata":"https://www.wikidata.org/wiki/Q170430","display_name":"Predation","level":2,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1017/s1351324914000175","doi":"https://doi.org/10.1017/s1351324914000175","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324914000175","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-b","jufo-3","poland-140","vabb-shw"],"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/4","score":0.5799999833106995,"display_name":"Quality education"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W10054769","https://openalex.org/W172155664","https://openalex.org/W1499275966","https://openalex.org/W1513168562","https://openalex.org/W1535150327","https://openalex.org/W1570629387","https://openalex.org/W1579838312","https://openalex.org/W1589180892","https://openalex.org/W1629199664","https://openalex.org/W1647053039","https://openalex.org/W1704572586","https://openalex.org/W1997049674","https://openalex.org/W2027529581","https://openalex.org/W2035967403","https://openalex.org/W2046932483","https://openalex.org/W2057200159","https://openalex.org/W2084128293","https://openalex.org/W2084603884","https://openalex.org/W2096291962","https://openalex.org/W2097835057","https://openalex.org/W2100000146","https://openalex.org/W2104599542","https://openalex.org/W2109772895","https://openalex.org/W2114550122","https://openalex.org/W2116912781","https://openalex.org/W2127863960","https://openalex.org/W2129914454","https://openalex.org/W2155942050","https://openalex.org/W2156988891","https://openalex.org/W2163489213","https://openalex.org/W2164107060","https://openalex.org/W2164280277","https://openalex.org/W2252192936","https://openalex.org/W2315348142","https://openalex.org/W2436001372","https://openalex.org/W4230872509"],"related_works":["https://openalex.org/W7077175516","https://openalex.org/W3167597168","https://openalex.org/W2522661147","https://openalex.org/W4296070391","https://openalex.org/W2745788963","https://openalex.org/W3161730088","https://openalex.org/W1521805656","https://openalex.org/W2219066094","https://openalex.org/W2924677654","https://openalex.org/W4416037349"],"abstract_inverted_index":{"Abstract":[0],"This":[1,114],"paper":[2,115],"describes":[3,116],"the":[4,12,19,37,57,78,109,117,121,148],"Kestrel":[5,22,48,144],"text":[6,42,65],"normalization":[7,43],"system,":[8,151],"a":[9],"component":[10],"of":[11,21,31,39,56,61,77,108,119,125,132,143,147,169],"Google":[13,149],"text-to-speech":[14],"synthesis":[15],"(TTS)":[16],"system.":[17],"At":[18],"core":[20],"are":[23,27,91,102],"text-normalization":[24],"grammars":[25,133],"that":[26],"compiled":[28],"into":[29,93],"libraries":[30],"weighted":[32],"finite-state":[33],"transducers":[34],"(WFSTs).":[35],"While":[36],"use":[38],"WFSTs":[40],"for":[41,134],"is":[44,66,164],"itself":[45],"not":[46],"new,":[47],"differs":[49],"from":[50],"previous":[51],"systems":[52],"in":[53,171],"its":[54],"separation":[55],"initialtokenization":[58],"and":[59,69,128,141,157,163,174],"classificationphase":[60],"analysis":[62],"fromverbalization.":[63],"Input":[64],"first":[67],"tokenized":[68],"different":[70],"tokens":[71],"classified":[72],"using":[73,112],"WFSTs.":[74,113],"As":[75],"part":[76,146],"classification,":[79],"detectedsemiotic":[80],"classes\u2013":[81],"expressions":[82],"such":[83],"as":[84,145],"currency":[85],"amounts,":[86],"dates,":[87],"times,":[88],"measure":[89],"phases,":[90],"parsed":[92],"protocol":[94,100,122],"buffers":[95,101],"(":[96],"https://code.google.com/p/protobuf/":[97],").":[98],"The":[99],"then":[103],"verbalized,":[104],"with":[105],"possible":[106],"reordering":[107],"elements,":[110],"again":[111],"architecture":[118],"Kestrel,":[120],"buffer":[123],"representations":[124],"semiotic":[126],"classes,":[127],"presents":[129],"some":[130],"examples":[131],"various":[135],"languages.":[136],"We":[137],"also":[138],"discuss":[139],"applications":[140],"deployments":[142],"TTS":[150],"which":[152],"runs":[153],"on":[154,160],"both":[155],"server":[156],"client":[158],"side":[159],"multiple":[161],"devices,":[162],"used":[165],"daily":[166],"by":[167],"millions":[168],"people":[170],"nineteen":[172],"languages":[173],"counting.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":5}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2016-06-24T00:00:00"}