{"id":"https://openalex.org/W4392903542","doi":"https://doi.org/10.1109/icassp48485.2024.10447144","title":"A Unified Front-End Framework for English Text-to-Speech Synthesis","display_name":"A Unified Front-End Framework for English Text-to-Speech Synthesis","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903542","doi":"https://doi.org/10.1109/icassp48485.2024.10447144"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447144","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447144","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5109607490","display_name":"Zelin Ying","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zelin Ying","raw_affiliation_strings":["Speech, Audio &#x0026; Music Intelligence (SAMI), ByteDance"],"affiliations":[{"raw_affiliation_string":"Speech, Audio &#x0026; Music Intelligence (SAMI), ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100369763","display_name":"Chen Li","orcid":"https://orcid.org/0000-0001-6249-8957"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Li","raw_affiliation_strings":["Speech, Audio &#x0026; Music Intelligence (SAMI), ByteDance"],"affiliations":[{"raw_affiliation_string":"Speech, Audio &#x0026; Music Intelligence (SAMI), ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101633403","display_name":"Yu Dong","orcid":"https://orcid.org/0000-0001-9837-602X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Dong","raw_affiliation_strings":["Speech, Audio &#x0026; Music Intelligence (SAMI), ByteDance"],"affiliations":[{"raw_affiliation_string":"Speech, Audio &#x0026; Music Intelligence (SAMI), ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072482416","display_name":"Qiuqiang Kong","orcid":"https://orcid.org/0000-0003-2864-0475"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiuqiang Kong","raw_affiliation_strings":["Speech, Audio &#x0026; Music Intelligence (SAMI), ByteDance"],"affiliations":[{"raw_affiliation_string":"Speech, Audio &#x0026; Music Intelligence (SAMI), ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103162279","display_name":"Qiao Tian","orcid":"https://orcid.org/0000-0002-4078-1273"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiao Tian","raw_affiliation_strings":["Speech, Audio &#x0026; Music Intelligence (SAMI), ByteDance"],"affiliations":[{"raw_affiliation_string":"Speech, Audio &#x0026; Music Intelligence (SAMI), ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101361769","display_name":"Yuanyuan Huo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuanyuan Huo","raw_affiliation_strings":["Speech, Audio &#x0026; Music Intelligence (SAMI), ByteDance"],"affiliations":[{"raw_affiliation_string":"Speech, Audio &#x0026; Music Intelligence (SAMI), ByteDance","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101664515","display_name":"Yuxuan Wang","orcid":"https://orcid.org/0009-0005-3508-3736"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuxuan Wang","raw_affiliation_strings":["Speech, Audio &#x0026; Music Intelligence (SAMI), ByteDance"],"affiliations":[{"raw_affiliation_string":"Speech, Audio &#x0026; Music Intelligence (SAMI), ByteDance","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5109607490"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3651,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.61762137,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"10181","last_page":"10185"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991999864578247,"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/T10028","display_name":"Topic Modeling","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9988999962806702,"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":0.7488932013511658},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.742485761642456},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.734997570514679},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6849826574325562},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.5925058722496033},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5755917429924011},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5540781617164612},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5468818545341492},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4978964328765869},{"id":"https://openalex.org/keywords/grapheme","display_name":"Grapheme","score":0.47494959831237793},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4364425837993622},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12060397863388062},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09494146704673767},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0940139889717102}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7488932013511658},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.742485761642456},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.734997570514679},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6849826574325562},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.5925058722496033},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5755917429924011},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5540781617164612},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5468818545341492},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4978964328765869},{"id":"https://openalex.org/C2776779415","wikidata":"https://www.wikidata.org/wiki/Q2545446","display_name":"Grapheme","level":3,"score":0.47494959831237793},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4364425837993622},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12060397863388062},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09494146704673767},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0940139889717102},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"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/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/C42360764","wikidata":"https://www.wikidata.org/wiki/Q83588","display_name":"Chemical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447144","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447144","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W1593247906","https://openalex.org/W2103085228","https://openalex.org/W2538246917","https://openalex.org/W2747175885","https://openalex.org/W2889523925","https://openalex.org/W2896457183","https://openalex.org/W2924677654","https://openalex.org/W2963609956","https://openalex.org/W2972437137","https://openalex.org/W3015651285","https://openalex.org/W3015680182","https://openalex.org/W3104681546","https://openalex.org/W3113850747","https://openalex.org/W3169750567","https://openalex.org/W4221160950","https://openalex.org/W4221166186","https://openalex.org/W4295276571","https://openalex.org/W4300558631","https://openalex.org/W4375799026","https://openalex.org/W4385245566","https://openalex.org/W6729005282","https://openalex.org/W6788095661","https://openalex.org/W6809893488"],"related_works":["https://openalex.org/W10581632","https://openalex.org/W1927421023","https://openalex.org/W3149582125","https://openalex.org/W157238252","https://openalex.org/W2169632867","https://openalex.org/W2465421051","https://openalex.org/W152045069","https://openalex.org/W652196294","https://openalex.org/W2368700418","https://openalex.org/W1965141925"],"abstract_inverted_index":{"The":[0,31],"front-end":[1,34,62,97],"is":[2],"a":[3,20,38,43,51,85],"critical":[4],"component":[5],"of":[6,37],"English":[7,32,60,95],"text-to-speech":[8,21],"(TTS)":[9],"systems,":[10],"responsible":[11],"for":[12,19,78],"extracting":[13],"linguistic":[14],"features":[15],"that":[16,89,103],"are":[17],"essential":[18],"model":[22],"to":[23],"synthesize":[24],"speech,":[25],"such":[26],"as":[27],"prosodies":[28],"and":[29,50,73],"phonemes.":[30],"TTS":[33,61,96],"typically":[35],"consists":[36],"text":[39],"normalization":[40],"(TN)":[41],"module,":[42,49],"prosody":[44,46],"word":[45],"phrase":[47],"(PWPP)":[48],"grapheme-to-phoneme":[52],"(G2P)":[53],"module.":[54,80],"However,":[55],"current":[56],"research":[57],"on":[58,65],"the":[59,69,91,94,104],"focuses":[63],"solely":[64],"individual":[66],"modules,":[67],"neglecting":[68],"interdependence":[70],"between":[71],"them":[72],"resulting":[74],"in":[75,111],"sub-optimal":[76],"performance":[77,110],"each":[79],"Therefore,":[81],"this":[82],"paper":[83],"proposes":[84],"unified":[86],"frontend":[87],"framework":[88],"captures":[90],"dependencies":[92],"among":[93],"modules.":[98,113],"Extensive":[99],"experiments":[100],"have":[101],"demonstrated":[102],"proposed":[105],"method":[106],"achieves":[107],"state-of-the-art":[108],"(SOTA)":[109],"all":[112]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}
