{"id":"https://openalex.org/W2054442733","doi":"https://doi.org/10.1109/slt.2012.6424237","title":"A grapheme-based method for automatic alignment of speech and text data","display_name":"A grapheme-based method for automatic alignment of speech and text data","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W2054442733","doi":"https://doi.org/10.1109/slt.2012.6424237","mag":"2054442733"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2012.6424237","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2012.6424237","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Spoken Language Technology Workshop (SLT)","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/A5018126799","display_name":"Adriana Stan","orcid":"https://orcid.org/0000-0003-2894-5770"},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Adriana Stan","raw_affiliation_strings":["Communications Department, Technical University of Cluj-Napoca, Cluj-Napoca, Romania","Communications Department, Technical University of Cluj-Napoca, G. Baritiu 26-28, 400027, Cluj-Napoca, Romania"],"affiliations":[{"raw_affiliation_string":"Communications Department, Technical University of Cluj-Napoca, Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]},{"raw_affiliation_string":"Communications Department, Technical University of Cluj-Napoca, G. Baritiu 26-28, 400027, Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102911387","display_name":"Peter Bell","orcid":"https://orcid.org/0000-0002-9597-9615"},"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":"Peter Bell","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","The Centre for Speech Technology Research, University of Edinburgh, 10 Crichton Street, Edinburgh EH8 9AB, United Kingdom"],"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, 10 Crichton Street, Edinburgh EH8 9AB, United Kingdom","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, Edinburgh, UK","The Centre for Speech Technology Research, University of Edinburgh, 10 Crichton Street, Edinburgh EH8 9AB, United Kingdom"],"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, 10 Crichton Street, Edinburgh EH8 9AB, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5018126799"],"corresponding_institution_ids":["https://openalex.org/I158333966"],"apc_list":null,"apc_paid":null,"fwci":8.3979,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.97520237,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"286","last_page":"290"},"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/T11309","display_name":"Music and Audio Processing","score":0.9987000226974487,"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/T12031","display_name":"Speech and dialogue systems","score":0.9948999881744385,"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/computer-science","display_name":"Computer science","score":0.857639729976654},{"id":"https://openalex.org/keywords/grapheme","display_name":"Grapheme","score":0.8510574698448181},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6788172125816345},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6159482002258301},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6094644665718079},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5950461030006409},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5800844430923462},{"id":"https://openalex.org/keywords/orthographic-projection","display_name":"Orthographic projection","score":0.5465594530105591},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5157409310340881},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.47693175077438354},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4687618911266327},{"id":"https://openalex.org/keywords/phonetic-transcription","display_name":"Phonetic transcription","score":0.437874436378479},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.41538697481155396},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4070702791213989},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.34221380949020386},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06719842553138733}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.857639729976654},{"id":"https://openalex.org/C2776779415","wikidata":"https://www.wikidata.org/wiki/Q2545446","display_name":"Grapheme","level":3,"score":0.8510574698448181},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6788172125816345},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6159482002258301},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6094644665718079},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5950461030006409},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5800844430923462},{"id":"https://openalex.org/C175694140","wikidata":"https://www.wikidata.org/wiki/Q980329","display_name":"Orthographic projection","level":2,"score":0.5465594530105591},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5157409310340881},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.47693175077438354},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4687618911266327},{"id":"https://openalex.org/C2777853878","wikidata":"https://www.wikidata.org/wiki/Q743569","display_name":"Phonetic transcription","level":2,"score":0.437874436378479},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.41538697481155396},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4070702791213989},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.34221380949020386},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06719842553138733},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/slt.2012.6424237","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2012.6424237","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.248.4009","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.248.4009","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cstr.inf.ed.ac.uk/downloads/publications/2012/grapheme_alignment_slt2012.pdf","raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:ec_fundedresources/d3aba114-b4a0-404a-bdae-8201ff435816","is_oa":false,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/d3aba114-b4a0-404a-bdae-8201ff435816","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W85707815","https://openalex.org/W1510837697","https://openalex.org/W1517939602","https://openalex.org/W1975113979","https://openalex.org/W2015412875","https://openalex.org/W2105961775","https://openalex.org/W2156513557","https://openalex.org/W2158666451","https://openalex.org/W2170980774","https://openalex.org/W2406986214","https://openalex.org/W2951143245","https://openalex.org/W6603477829","https://openalex.org/W6654102529","https://openalex.org/W6683326479","https://openalex.org/W6713583454"],"related_works":["https://openalex.org/W2497489645","https://openalex.org/W2161573742","https://openalex.org/W97919259","https://openalex.org/W2023797014","https://openalex.org/W2462492290","https://openalex.org/W2606277428","https://openalex.org/W2115782554","https://openalex.org/W3124002070","https://openalex.org/W4250156791","https://openalex.org/W3037190132"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,16,46,68,80,111],"method":[4,92],"for":[5,15,54],"automatic":[6],"alignment":[7],"of":[8,42,71,83,85],"speech":[9,34,44,75,87,106],"data":[10],"with":[11,45],"unsynchronised,":[12],"imperfect":[13],"transcripts,":[14,35,109],"domain":[17],"where":[18],"no":[19],"initial":[20],"acoustic":[21,27],"models":[22],"are":[23,37,104],"available.":[24],"Using":[25],"grapheme-based":[26],"models,":[28],"word":[29,52],"skip":[30],"networks":[31],"and":[32,50,76,78,96,101,107,110],"orthographic":[33],"we":[36],"able":[38],"to":[39],"harvest":[40],"55%":[41],"the":[43,55,63,74,86,97,105],"93%":[47],"utterance-level":[48],"accuracy":[49,53],"99%":[51],"produced":[56],"transcriptions.":[57],"The":[58,91],"work":[59],"is":[60,67,88,93],"based":[61],"on":[62],"assumption":[64],"that":[65,79],"there":[66],"high":[69],"degree":[70],"correspondence":[72],"between":[73],"text,":[77],"full":[81],"transcription":[82],"all":[84],"not":[89],"required.":[90],"language":[94],"independent":[95],"only":[98],"prior":[99],"knowledge":[100],"resources":[102],"required":[103],"text":[108],"few":[112],"minor":[113],"user":[114],"interventions.":[115]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
