{"id":"https://openalex.org/W4375799026","doi":"https://doi.org/10.1109/taslp.2023.3273414","title":"Improving Seq2Seq TTS Frontends With Transcribed Speech Audio","display_name":"Improving Seq2Seq TTS Frontends With Transcribed Speech Audio","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4375799026","doi":"https://doi.org/10.1109/taslp.2023.3273414"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3273414","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3273414","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/files/346892940/Improving_Seq3Seq_SUN_DOA26042023_AFV_CC_BY.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012731056","display_name":"Siqi Sun","orcid":"https://orcid.org/0000-0002-8947-4207"},"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":"Siqi Sun","raw_affiliation_strings":["University of Edinburgh, Edinburgh, U.K"],"raw_orcid":"https://orcid.org/0000-0002-8947-4207","affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, U.K","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055415493","display_name":"Korin Richmond","orcid":"https://orcid.org/0000-0003-1450-8270"},"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":"Korin Richmond","raw_affiliation_strings":["University of Edinburgh, Edinburgh, U.K"],"raw_orcid":"https://orcid.org/0000-0003-1450-8270","affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, U.K","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100662187","display_name":"Hao Tang","orcid":"https://orcid.org/0000-0002-2445-2605"},"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":"Hao Tang","raw_affiliation_strings":["University of Edinburgh, Edinburgh, U.K"],"raw_orcid":"https://orcid.org/0000-0002-2445-2605","affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, U.K","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":0.261,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.62221864,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"31","issue":null,"first_page":"1940","last_page":"1952"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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":0.9991999864578247,"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/computer-science","display_name":"Computer science","score":0.760274350643158},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.689183235168457},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6725440621376038},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6518281102180481},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6055170297622681},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.5805845260620117},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39056140184402466},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14578983187675476}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.760274350643158},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.689183235168457},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6725440621376038},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6518281102180481},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6055170297622681},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.5805845260620117},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39056140184402466},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14578983187675476},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2023.3273414","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3273414","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/bf9d007f-6936-4524-8322-2f2f026fc92b","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/bf9d007f-6936-4524-8322-2f2f026fc92b","pdf_url":"https://www.research.ed.ac.uk/files/346892940/Improving_Seq3Seq_SUN_DOA26042023_AFV_CC_BY.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sun, S, Richmond, K & Tang, H 2023, 'Improving Seq2Seq TTS Frontends with Transcribed Speech Audio', IEEE/ACM Transactions on Audio, Speech and Language Processing, vol. 31, pp. 1940-1952. https://doi.org/10.1109/TASLP.2023.3273414","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/bf9d007f-6936-4524-8322-2f2f026fc92b","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/files/346892940/Improving_Seq3Seq_SUN_DOA26042023_AFV_CC_BY.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sun, S, Richmond, K & Tang, H 2023, 'Improving Seq2Seq TTS Frontends with Transcribed Speech Audio', IEEE/ACM Transactions on Audio, Speech and Language Processing, vol. 31, pp. 1940-1952. https://doi.org/10.1109/TASLP.2023.3273414","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:publications/bf9d007f-6936-4524-8322-2f2f026fc92b","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/bf9d007f-6936-4524-8322-2f2f026fc92b","pdf_url":"https://www.research.ed.ac.uk/files/346892940/Improving_Seq3Seq_SUN_DOA26042023_AFV_CC_BY.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sun, S, Richmond, K & Tang, H 2023, 'Improving Seq2Seq TTS Frontends with Transcribed Speech Audio', IEEE/ACM Transactions on Audio, Speech and Language Processing, vol. 31, pp. 1940-1952. https://doi.org/10.1109/TASLP.2023.3273414","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5600000023841858}],"awards":[{"id":"https://openalex.org/G373773752","display_name":null,"funder_award_id":"EP/S022481/1","funder_id":"https://openalex.org/F4320314731","funder_display_name":"UK Research and Innovation"}],"funders":[{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"},{"id":"https://openalex.org/F4320320332","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4375799026.pdf","grobid_xml":"https://content.openalex.org/works/W4375799026.grobid-xml"},"referenced_works_count":61,"referenced_works":["https://openalex.org/W182831726","https://openalex.org/W1494198834","https://openalex.org/W1510319275","https://openalex.org/W1522301498","https://openalex.org/W1582482241","https://openalex.org/W1593247906","https://openalex.org/W1902237438","https://openalex.org/W1915251500","https://openalex.org/W2046932483","https://openalex.org/W2170980774","https://openalex.org/W2293883202","https://openalex.org/W2477293991","https://openalex.org/W2538246917","https://openalex.org/W2591927543","https://openalex.org/W2749648329","https://openalex.org/W2766812927","https://openalex.org/W2888779557","https://openalex.org/W2924677654","https://openalex.org/W2945656493","https://openalex.org/W2962784628","https://openalex.org/W2962826786","https://openalex.org/W2963240019","https://openalex.org/W2963299674","https://openalex.org/W2963609956","https://openalex.org/W2963913768","https://openalex.org/W2963945466","https://openalex.org/W2964243274","https://openalex.org/W2972437137","https://openalex.org/W2972489453","https://openalex.org/W2972610613","https://openalex.org/W2972677740","https://openalex.org/W2983833314","https://openalex.org/W3011874709","https://openalex.org/W3015651285","https://openalex.org/W3015680182","https://openalex.org/W3016160783","https://openalex.org/W3016224472","https://openalex.org/W3033411150","https://openalex.org/W3037482713","https://openalex.org/W3091928890","https://openalex.org/W3113217815","https://openalex.org/W3161730088","https://openalex.org/W3174758275","https://openalex.org/W3197294703","https://openalex.org/W3197324626","https://openalex.org/W3198020407","https://openalex.org/W3198848374","https://openalex.org/W3203103957","https://openalex.org/W4200300291","https://openalex.org/W4220890336","https://openalex.org/W4221155853","https://openalex.org/W4224629880","https://openalex.org/W4287854810","https://openalex.org/W4295276571","https://openalex.org/W6631190155","https://openalex.org/W6729005282","https://openalex.org/W6745697700","https://openalex.org/W6778823374","https://openalex.org/W6784545093","https://openalex.org/W6796730497","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W2183593636","https://openalex.org/W2350724007","https://openalex.org/W2355751417","https://openalex.org/W2423284978","https://openalex.org/W2083922162","https://openalex.org/W2000075989","https://openalex.org/W3006486861","https://openalex.org/W4220683390","https://openalex.org/W2776838583","https://openalex.org/W2359469050"],"abstract_inverted_index":{"Due":[0],"to":[1,34,96,108,133],"the":[2,80,85,98,110,116,127,144,155,160],"data":[3],"inefficiency":[4],"and":[5,36,65,75,104,152],"low":[6],"speech":[7,102,150],"quality":[8],"of":[9,68,118,146,159],"grapheme-based":[10],"end-to-end":[11],"text-to-speech":[12],"(TTS),":[13],"having":[14],"a":[15,28,61,91],"separate":[16],"high-performance":[17],"TTS":[18,29,58],"linguistic":[19,42],"frontend":[20,30,59,64],"is":[21,31],"still":[22],"commonly":[23],"regarded":[24],"as":[25],"necessary.":[26],"However,":[27],"itself":[32],"difficult":[33],"build":[35],"maintain,":[37],"since":[38],"it":[39,140],"requires":[40],"abundant":[41],"knowledge":[43],"for":[44,135],"its":[45],"construction.":[46],"In":[47,138],"this":[48,88],"paper,":[49],"we":[50],"start":[51],"by":[52,84],"bootstrapping":[53],"an":[54],"integrated":[55],"sequence-to-sequence":[56],"(Seq2Seq)":[57],"using":[60],"pre-existing":[62],"pipeline-based":[63,86],"large":[66],"amounts":[67],"unlabelled":[69],"normalized":[70],"text,":[71],"achieving":[72],"promising":[73],"memorization":[74],"generalisation":[76],"abilities.":[77],"To":[78],"overcome":[79],"performance":[81,158],"limitation":[82],"imposed":[83],"frontend,":[87],"work":[89],"proposes":[90],"Forced":[92],"Alignment":[93],"(FA)":[94],"method":[95],"decode":[97],"pronunciations":[99],"from":[100,131,148],"transcribed":[101,149],"audio":[103,151],"then":[105],"use":[106],"them":[107],"update":[109],"Seq2Seq":[111,161],"frontend.":[112,162],"Our":[113],"experiments":[114],"demonstrate":[115],"effectiveness":[117],"our":[119],"proposed":[120],"FA":[121],"method,":[122],"which":[123],"can":[124,141],"significantly":[125],"improve":[126,154],"word":[128],"token":[129],"accuracy":[130],"52.6%":[132],"91.2%":[134],"out-of-dictionary":[136],"words.":[137],"addition,":[139],"also":[142],"correct":[143],"pronunciation":[145],"homographs":[147],"potentially":[153],"homograph":[156],"disambiguation":[157]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2025-10-10T00:00:00"}