{"id":"https://openalex.org/W2982661195","doi":"https://doi.org/10.26615/issn.2603-2821.2019_007","title":"Towards Accurate Text Verbalization for ASR Based on Audio Alignment","display_name":"Towards Accurate Text Verbalization for ASR Based on Audio Alignment","publication_year":2019,"publication_date":"2019-09-15","ids":{"openalex":"https://openalex.org/W2982661195","doi":"https://doi.org/10.26615/issn.2603-2821.2019_007","mag":"2982661195"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.26615/issn.2603-2821.2019_007","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://doi.org/10.26615/issn.2603-2821.2019_007","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087988731","display_name":"Diana Geneva","orcid":null},"institutions":[{"id":"https://openalex.org/I4210163063","display_name":"Institute of Information and Communication Technologies","ror":"https://ror.org/05fpsjc82","country_code":"BG","type":"facility","lineage":["https://openalex.org/I24768866","https://openalex.org/I4210163063"]}],"countries":["BG"],"is_corresponding":false,"raw_author_name":"Diana Geneva","raw_affiliation_strings":["IICT -BAS 2, Acad. G. Bonchev Str. 1113 Sofia, Bulgaria"],"affiliations":[{"raw_affiliation_string":"IICT -BAS 2, Acad. G. Bonchev Str. 1113 Sofia, Bulgaria","institution_ids":["https://openalex.org/I4210163063"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008307349","display_name":"Georgi Shopov","orcid":"https://orcid.org/0000-0002-7649-0064"},"institutions":[{"id":"https://openalex.org/I4210163063","display_name":"Institute of Information and Communication Technologies","ror":"https://ror.org/05fpsjc82","country_code":"BG","type":"facility","lineage":["https://openalex.org/I24768866","https://openalex.org/I4210163063"]}],"countries":["BG"],"is_corresponding":false,"raw_author_name":"Georgi Shopov","raw_affiliation_strings":["IICT -BAS 2, Acad. G. Bonchev Str. 1113 Sofia, Bulgaria"],"affiliations":[{"raw_affiliation_string":"IICT -BAS 2, Acad. G. Bonchev Str. 1113 Sofia, Bulgaria","institution_ids":["https://openalex.org/I4210163063"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":0,"max":61},"biblio":{"volume":null,"issue":null,"first_page":"39","last_page":"47"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9999,"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":0.9999,"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":0.9992,"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":0.9992,"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":[],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.83272064},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6133503},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.587746},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5640677},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.56267244},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.54017687},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49844098},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08955577},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.26615/issn.2603-2821.2019_007","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.26615/issn.2603-2821.2019_007","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[{"display_name":"Quality education","id":"https://metadata.un.org/sdg/4","score":0.78}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":14,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1631260214","https://openalex.org/W1966147466","https://openalex.org/W1970026646","https://openalex.org/W2026369565","https://openalex.org/W2117444496","https://openalex.org/W2250398284","https://openalex.org/W2397159106","https://openalex.org/W2402146185","https://openalex.org/W2577358322","https://openalex.org/W2745845505","https://openalex.org/W2748645244","https://openalex.org/W2976887715"],"related_works":["https://openalex.org/W4388331409","https://openalex.org/W4387493491","https://openalex.org/W2904225411","https://openalex.org/W2651370314","https://openalex.org/W2370205415","https://openalex.org/W2323686453","https://openalex.org/W2169921015","https://openalex.org/W2061937230","https://openalex.org/W1975570126","https://openalex.org/W1961128080"],"abstract_inverted_index":{"Verbalization":[0],"of":[1,42,63,72,103,108,118,124],"non-lexical":[2],"linguistic":[3],"units":[4],"plays":[5],"an":[6],"important":[7],"role":[8],"in":[9,100],"language":[10],"modeling":[11],"for":[12,60,69],"automatic":[13],"speech":[14,131],"recognition":[15,102],"systems.Most":[16],"verbalization":[17,71,94,119],"methods":[18],"require":[19],"valuable":[20],"resources":[21],"such":[22],"as":[23],"ground":[24],"truth,":[25],"large":[26],"training":[27],"corpus":[28],"and":[29,56,82],"expert":[30],"knowledge":[31],"which":[32],"are":[33,50],"often":[34],"unavailable.On":[35],"the":[36,54,61,80,106,115,122],"other":[37],"hand":[38],"a":[39,67,90,97],"considerable":[40],"amount":[41],"audio":[43,73,85],"data":[44],"along":[45],"with":[46],"its":[47],"transcribed":[48],"text":[49],"freely":[51],"available":[52],"on":[53,76,121,128],"Internet":[55],"could":[57],"be":[58],"utilized":[59],"task":[62],"verbalization.This":[64],"paper":[65],"presents":[66],"methodology":[68],"accurate":[70],"transcriptions":[74,81],"based":[75],"phone-level":[77],"alignment":[78],"between":[79],"their":[83],"corresponding":[84],"recordings.Comparing":[86],"this":[87,110],"approach":[88,111],"to":[89],"more":[91],"general":[92],"rule-based":[93],"method":[95],"shows":[96],"significant":[98],"improvement":[99],"ASR":[101],"nonlexical":[104],"units.In":[105],"process":[107],"evaluating":[109],"we":[112],"also":[113],"expose":[114],"indirect":[116],"influence":[117],"accuracy":[120],"quality":[123],"acoustic":[125],"models":[126],"trained":[127],"automatically":[129],"derived":[130],"corpora.":[132]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2982661195","counts_by_year":[],"updated_date":"2024-12-07T02:06:34.304372","created_date":"2019-11-08"}