{"id":"https://openalex.org/W4378464718","doi":"https://doi.org/10.48550/arxiv.2305.13612","title":"FluentSpeech: Stutter-Oriented Automatic Speech Editing with Context-Aware Diffusion Models","display_name":"FluentSpeech: Stutter-Oriented Automatic Speech Editing with Context-Aware Diffusion Models","publication_year":2023,"publication_date":"2023-05-23","ids":{"openalex":"https://openalex.org/W4378464718","doi":"https://doi.org/10.48550/arxiv.2305.13612"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2305.13612","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.13612","pdf_url":"https://arxiv.org/pdf/2305.13612","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2305.13612","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083611896","display_name":"Ziyue Karen Jiang","orcid":"https://orcid.org/0009-0007-4158-4689"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Ziyue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100379388","display_name":"Qian Yang","orcid":"https://orcid.org/0009-0009-8975-6982"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Qian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101230918","display_name":"Jialong Zuo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zuo, Jialong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016502904","display_name":"Zhenhui Ye","orcid":"https://orcid.org/0000-0002-7105-014X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Zhenhui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011787904","display_name":"Rongjie Huang","orcid":"https://orcid.org/0000-0002-1695-9000"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Rongjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075486968","display_name":"Yi Ren","orcid":"https://orcid.org/0000-0002-3665-700X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ren, Yi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5079260216","display_name":"Zhou Zhao","orcid":"https://orcid.org/0000-0001-6121-0384"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9915000200271606,"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":0.9915000200271606,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9674999713897705,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.963100016117096,"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":0.8187543153762817},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7357176542282104},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6829816699028015},{"id":"https://openalex.org/keywords/stuttering","display_name":"Stuttering","score":0.5836893916130066},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.555973470211029},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5246130228042603},{"id":"https://openalex.org/keywords/fluency","display_name":"Fluency","score":0.5188778042793274},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.4637501835823059},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3966692090034485},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3384139835834503},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06148606538772583}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8187543153762817},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7357176542282104},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6829816699028015},{"id":"https://openalex.org/C2781371259","wikidata":"https://www.wikidata.org/wiki/Q186676","display_name":"Stuttering","level":2,"score":0.5836893916130066},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.555973470211029},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5246130228042603},{"id":"https://openalex.org/C2777413886","wikidata":"https://www.wikidata.org/wiki/Q3276013","display_name":"Fluency","level":2,"score":0.5188778042793274},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.4637501835823059},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3966692090034485},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3384139835834503},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06148606538772583},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2305.13612","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.13612","pdf_url":"https://arxiv.org/pdf/2305.13612","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2305.13612","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2305.13612","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2305.13612","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.13612","pdf_url":"https://arxiv.org/pdf/2305.13612","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4300000071525574}],"awards":[{"id":"https://openalex.org/G6050241676","display_name":"\u57fa\u4e8e\u5f31\u6807\u6ce8\u7684\u8de8\u6a21\u6001\u89c6\u9891\u5b9a\u4f4d\u65b9\u6cd5\u7814\u7a76","funder_award_id":"62072397","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7528510259","display_name":"\u57fa\u4e8e\u5927\u89c4\u6a21\u8de8\u5a92\u4f53\u77e5\u8bc6\u7f51\u7edc\u7684\u590d\u6742\u89c6\u9891\u95ee\u7b54\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61836002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4378464718.pdf","grobid_xml":"https://content.openalex.org/works/W4378464718.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2348937403","https://openalex.org/W2088087094","https://openalex.org/W2606084965","https://openalex.org/W604959964","https://openalex.org/W2043322848","https://openalex.org/W1483627603","https://openalex.org/W2103044274","https://openalex.org/W2163543546","https://openalex.org/W2036832189","https://openalex.org/W2022288375"],"abstract_inverted_index":{"Stutter":[0],"removal":[1],"is":[2],"an":[3],"essential":[4],"scenario":[5],"in":[6,32,65,174],"the":[7,14,19,29,33,42,50,57,63,88,92,106,110,135,169],"field":[8],"of":[9,38,94,171,176],"speech":[10,15,22,74,120,127,155,173],"editing.":[11,156],"However,":[12],"when":[13],"recording":[16],"contains":[17,125],"stutters,":[18,51],"existing":[20],"text-based":[21],"editing":[23,75,121],"approaches":[24],"still":[25],"suffer":[26],"from:":[27],"1)":[28,78],"over-smoothing":[30],"problem":[31],"edited":[34,58],"speech;":[35],"2)":[36,97],"lack":[37],"robustness":[39],"due":[40],"to":[41,48,55,104,133],"noise":[43],"introduced":[44],"by":[45],"stutter;":[46],"3)":[47,113],"remove":[49],"users":[52],"are":[53],"required":[54],"determine":[56],"region":[59],"manually.":[60],"To":[61],"tackle":[62],"challenges":[64],"stutter":[66,101,107,131,137],"removal,":[67],"we":[68,79,98,114],"propose":[69,80,116],"FluentSpeech,":[70],"a":[71,81,100,117],"stutter-oriented":[72,118],"automatic":[73,119,136],"model.":[76,139],"Specifically,":[77],"context-aware":[82],"diffusion":[83],"model":[84,150],"that":[85,124,148,164],"iteratively":[86],"refines":[87],"modified":[89],"mel-spectrogram":[90],"with":[91,129],"guidance":[93],"context":[95],"features;":[96],"introduce":[99],"predictor":[102],"module":[103],"inject":[105],"information":[108],"into":[109],"hidden":[111],"sequence;":[112],"also":[115],"(SASE)":[122],"dataset":[123,162],"spontaneous":[126],"recordings":[128],"time-aligned":[130],"labels":[132],"train":[134],"localization":[138],"Experimental":[140],"results":[141],"on":[142,154,159],"VCTK":[143],"and":[144,178,182],"LibriTTS":[145],"datasets":[146],"demonstrate":[147],"our":[149,160],"achieves":[151],"state-of-the-art":[152],"performance":[153],"Further":[157],"experiments":[158],"SASE":[161],"show":[163],"FluentSpeech":[165],"can":[166,185],"effectively":[167],"improve":[168],"fluency":[170],"stuttering":[172],"terms":[175],"objective":[177],"subjective":[179],"metrics.":[180],"Code":[181],"audio":[183],"samples":[184],"be":[186],"found":[187],"at":[188],"https://github.com/Zain-Jiang/Speech-Editing-Toolkit.":[189]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2023-05-27T00:00:00"}