{"id":"https://openalex.org/W4225596771","doi":"https://doi.org/10.1109/asru51503.2021.9688051","title":"EditSpeech: A Text Based Speech Editing System Using Partial Inference and Bidirectional Fusion","display_name":"EditSpeech: A Text Based Speech Editing System Using Partial Inference and Bidirectional Fusion","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4225596771","doi":"https://doi.org/10.1109/asru51503.2021.9688051"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9688051","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688051","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5006527442","display_name":"Daxin Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Daxin Tan","raw_affiliation_strings":["The Chinese University of Hong Kong,Department of Electronic Engineering,Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Department of Electronic Engineering,Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044738402","display_name":"Liqun Deng","orcid":"https://orcid.org/0009-0006-7242-0794"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqun Deng","raw_affiliation_strings":["Huawei Noah&#x0027;s Ark Lab,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah&#x0027;s Ark Lab,Shenzhen,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083831776","display_name":"Yu Ting Yeung","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Ting Yeung","raw_affiliation_strings":["Huawei Noah&#x0027;s Ark Lab,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah&#x0027;s Ark Lab,Shenzhen,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086603207","display_name":"Xin Jiang","orcid":"https://orcid.org/0000-0002-9117-8247"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Jiang","raw_affiliation_strings":["Huawei Noah&#x0027;s Ark Lab,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah&#x0027;s Ark Lab,Shenzhen,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100373698","display_name":"Xiao Dong Chen","orcid":"https://orcid.org/0000-0002-0150-0491"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Chen","raw_affiliation_strings":["Huawei Noah&#x0027;s Ark Lab,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah&#x0027;s Ark Lab,Shenzhen,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001795601","display_name":"Tan Lee","orcid":"https://orcid.org/0000-0002-7089-3436"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tan Lee","raw_affiliation_strings":["The Chinese University of Hong Kong,Department of Electronic Engineering,Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Department of Electronic Engineering,Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9025,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.89057301,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"626","last_page":"633"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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/T11309","display_name":"Music and Audio Processing","score":0.9984999895095825,"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/utterance","display_name":"Utterance","score":0.8124361038208008},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7511578798294067},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7407602667808533},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6584233045578003},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.6311250925064087},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.624539315700531},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5861071944236755},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47448351979255676},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.45084550976753235},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42596641182899475}],"concepts":[{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.8124361038208008},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7511578798294067},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7407602667808533},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6584233045578003},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.6311250925064087},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.624539315700531},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5861071944236755},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47448351979255676},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.45084550976753235},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42596641182899475},{"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru51503.2021.9688051","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688051","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G5660791893","display_name":null,"funder_award_id":"KPF20QEP26","funder_id":"https://openalex.org/F4320322942","funder_display_name":"Chinese University of Hong Kong"}],"funders":[{"id":"https://openalex.org/F4320322942","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1980618402","https://openalex.org/W2058733260","https://openalex.org/W2428180336","https://openalex.org/W2747874407","https://openalex.org/W2766812927","https://openalex.org/W2793703241","https://openalex.org/W2903739847","https://openalex.org/W2935811960","https://openalex.org/W2963091184","https://openalex.org/W2963300588","https://openalex.org/W2964243274","https://openalex.org/W2969521066","https://openalex.org/W2970006822","https://openalex.org/W2971753973","https://openalex.org/W2998572311","https://openalex.org/W3015338123","https://openalex.org/W3026874504","https://openalex.org/W3033411150","https://openalex.org/W3092028330","https://openalex.org/W3094002217","https://openalex.org/W3096159803","https://openalex.org/W3130821015","https://openalex.org/W3160353145","https://openalex.org/W3160438760","https://openalex.org/W4240592325","https://openalex.org/W6631190155","https://openalex.org/W6767111847","https://openalex.org/W6767453231","https://openalex.org/W6777694618","https://openalex.org/W6778823374","https://openalex.org/W6783867762","https://openalex.org/W6785090365"],"related_works":["https://openalex.org/W4391272374","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W40885451","https://openalex.org/W2108985546","https://openalex.org/W2081919107","https://openalex.org/W2433276473","https://openalex.org/W2535215250","https://openalex.org/W1813881148","https://openalex.org/W1537411440"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"the":[3,63,68,84,88],"design,":[4],"implementation":[5],"and":[6,23,39,55,71,78,97,101,107,124],"evaluation":[7,109],"of":[8,25,87,120],"a":[9,17,28,47,114],"speech":[10,30,37,126],"editing":[11],"system,":[12],"named":[13],"EditSpeech,":[14],"which":[15],"allows":[16],"user":[18],"to":[19,60,67,83],"perform":[20],"deletion,":[21],"insertion":[22],"replacement":[24],"words":[26],"in":[27,36,103,118],"given":[29],"utterance,":[31],"without":[32],"causing":[33],"audible":[34],"degradation":[35],"quality":[38],"naturalness.":[40],"The":[41,92],"EditSpeech":[42,93,112],"system":[43,94],"is":[44,90,95],"developed":[45,96],"upon":[46],"neural":[48],"text-to-speech":[49],"(NTTS)":[50],"synthesis":[51],"framework.":[52],"Partial":[53],"inference":[54],"bidirectional":[56],"fusion":[57],"are":[58,130],"proposed":[59],"effectively":[61],"incorporate":[62],"contextual":[64],"information":[65],"related":[66],"edited":[69],"region":[70],"achieve":[72],"smooth":[73],"transition":[74],"at":[75],"both":[76],"left":[77],"right":[79],"boundaries.":[80],"Distortion":[81],"introduced":[82],"unmodified":[85],"parts":[86],"utterance":[89],"alleviated.":[91],"evaluated":[98],"on":[99],"English":[100],"Chinese":[102],"multi-speaker":[104],"scenarios.":[105],"Objective":[106],"subjective":[108],"demonstrate":[110],"that":[111],"outperforms":[113],"few":[115],"baseline":[116],"systems":[117],"terms":[119],"low":[121],"spectral":[122],"distortion":[123],"preferred":[125],"quality.":[127],"Audio":[128],"samples":[129],"available":[131],"online":[132],"for":[133],"demonstration":[134],"<sup":[135,138],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[136,139],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[137,140],"https://daxintan-cuhk.github.io/EditSpeech/.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
