{"id":"https://openalex.org/W3130821015","doi":"https://doi.org/10.1109/icassp39728.2021.9414633","title":"Context-Aware Prosody Correction for Text-Based Speech Editing","display_name":"Context-Aware Prosody Correction for Text-Based Speech Editing","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3130821015","doi":"https://doi.org/10.1109/icassp39728.2021.9414633","mag":"3130821015"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414633","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414633","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2102.08328","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102779961","display_name":"Max Morrison","orcid":"https://orcid.org/0000-0002-6082-5157"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Max Morrison","raw_affiliation_strings":["Northwestern University, Evanston, IL, USA","Northwestern university, EVANSTON, IL, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University, Evanston, IL, USA","institution_ids":["https://openalex.org/I111979921"]},{"raw_affiliation_string":"Northwestern university, EVANSTON, IL, USA#TAB#","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084833074","display_name":"Lucas Rencker","orcid":"https://orcid.org/0000-0002-9332-6602"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lucas Rencker","raw_affiliation_strings":["University of Surrey, Guildford, UK","Univ. of Surrey, Guildford, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey, Guildford, UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Univ. of Surrey, Guildford, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100702050","display_name":"Zeyu Jin","orcid":"https://orcid.org/0000-0003-0161-5915"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zeyu Jin","raw_affiliation_strings":["Adobe Research, San Francisco, CA, USA","[Adobe Research, San Francisco, CA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research, San Francisco, CA, USA","institution_ids":["https://openalex.org/I1306409833"]},{"raw_affiliation_string":"[Adobe Research, San Francisco, CA, USA]","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045694117","display_name":"Nicholas J. Bryan","orcid":"https://orcid.org/0000-0003-1469-7278"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicholas J. Bryan","raw_affiliation_strings":["Adobe Research, San Francisco, CA, USA","[Adobe Research, San Francisco, CA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research, San Francisco, CA, USA","institution_ids":["https://openalex.org/I1306409833"]},{"raw_affiliation_string":"[Adobe Research, San Francisco, CA, USA]","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085104947","display_name":"Juan-Pablo C\u00e1ceres","orcid":"https://orcid.org/0000-0002-5354-6555"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juan-Pablo Caceres","raw_affiliation_strings":["Adobe Research, San Francisco, CA, USA","[Adobe Research, San Francisco, CA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research, San Francisco, CA, USA","institution_ids":["https://openalex.org/I1306409833"]},{"raw_affiliation_string":"[Adobe Research, San Francisco, CA, USA]","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102878078","display_name":"Bryan Pardo","orcid":"https://orcid.org/0000-0002-1427-6492"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bryan Pardo","raw_affiliation_strings":["Northwestern University, Evanston, IL, USA","Northwestern university, EVANSTON, IL, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University, Evanston, IL, USA","institution_ids":["https://openalex.org/I111979921"]},{"raw_affiliation_string":"Northwestern university, EVANSTON, IL, USA#TAB#","institution_ids":["https://openalex.org/I111979921"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7038","last_page":"7042"},"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9984999895095825,"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/T11309","display_name":"Music and Audio Processing","score":0.9980999827384949,"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":0.7908994555473328},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.7563647627830505},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7029370069503784},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5435431599617004},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.45972296595573425},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.4527941942214966},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.4448162913322449},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.43011346459388733},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4270440936088562},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40202271938323975},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3979471027851105},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.09034320712089539}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7908994555473328},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.7563647627830505},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7029370069503784},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5435431599617004},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.45972296595573425},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.4527941942214966},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.4448162913322449},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.43011346459388733},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4270440936088562},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40202271938323975},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3979471027851105},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.09034320712089539},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414633","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414633","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2102.08328","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.08328","pdf_url":"https://arxiv.org/pdf/2102.08328","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3130821015","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2102.08328.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2102.08328","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2102.08328","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.17023/3nc9-y607","is_oa":true,"landing_page_url":"https://doi.org/10.17023/3nc9-y607","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Audiovisual"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2102.08328","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.08328","pdf_url":"https://arxiv.org/pdf/2102.08328","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3130821015.pdf","grobid_xml":"https://content.openalex.org/works/W3130821015.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W36638734","https://openalex.org/W1993950587","https://openalex.org/W2029996593","https://openalex.org/W2058733260","https://openalex.org/W2428180336","https://openalex.org/W2471520273","https://openalex.org/W2737697117","https://openalex.org/W2884225676","https://openalex.org/W2949117887","https://openalex.org/W2962866891","https://openalex.org/W2963091184","https://openalex.org/W2963300588","https://openalex.org/W2963432880","https://openalex.org/W2970006822","https://openalex.org/W2970730223","https://openalex.org/W3034949308","https://openalex.org/W3096159803","https://openalex.org/W3097003111","https://openalex.org/W3216401400","https://openalex.org/W4253325818","https://openalex.org/W6601463856","https://openalex.org/W6638667902","https://openalex.org/W6752888775","https://openalex.org/W6763832098","https://openalex.org/W6767111847","https://openalex.org/W6778823374","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W3160438760","https://openalex.org/W2101762720","https://openalex.org/W1980618402","https://openalex.org/W2587786618","https://openalex.org/W3198217962","https://openalex.org/W3186965183","https://openalex.org/W2990883660","https://openalex.org/W2031249898","https://openalex.org/W2012452355","https://openalex.org/W3095409311","https://openalex.org/W2551521043","https://openalex.org/W157135116","https://openalex.org/W2005865674","https://openalex.org/W3015215494","https://openalex.org/W2737658251","https://openalex.org/W2550017779","https://openalex.org/W2572999154","https://openalex.org/W3174674681","https://openalex.org/W2911571030","https://openalex.org/W2972463723"],"abstract_inverted_index":{"Text-based":[0],"speech":[1,8,22,85],"editors":[2],"expedite":[3],"the":[4,82,87,97,120],"process":[5],"of":[6,27,39,60,70,84],"editing":[7,12,59],"recordings":[9,34],"by":[10,119],"permitting":[11],"via":[13],"intuitive":[14],"cut,":[15],"copy,":[16],"and":[17,89,105,108,142],"paste":[18],"operations":[19],"on":[20,81],"a":[21,50,68,102,111,125,133,138],"transcript.":[23],"A":[24],"major":[25],"drawback":[26],"current":[28],"systems,":[29],"however,":[30],"is":[31],"that":[32,78],"edited":[33,43],"often":[35],"sound":[36],"unnatural":[37],"because":[38],"prosody":[40,76,83],"mismatches":[41],"around":[42],"regions.":[44],"In":[45],"our":[46,130],"work,":[47],"we":[48,65],"propose":[49],"new":[51],"context-aware":[52],"method":[53,107],"for":[54],"more":[55],"natural":[56],"sounding":[57],"text-based":[58],"speech.":[61],"To":[62],"do":[63],"so,":[64],"1)":[66],"use":[67,96],"series":[69],"neural":[71,113],"networks":[72],"to":[73,91,100,115,123],"generate":[74],"salient":[75],"features":[77,99],"are":[79],"dependent":[80],"surrounding":[86],"edit":[88],"amenable":[90],"fine-grained":[92],"user":[93],"control":[94,101],"2)":[95],"generated":[98],"standard":[103],"pitch-shift":[104],"time-stretch":[106],"3)":[109],"apply":[110],"denoising":[112],"network":[114],"remove":[116],"artifacts":[117],"induced":[118],"signal":[121],"manipulation":[122],"yield":[124],"high-fidelity":[126],"result.":[127],"We":[128],"evaluate":[129],"approach":[131],"using":[132],"subjective":[134],"listening":[135],"test,":[136],"provide":[137],"detailed":[139],"comparative":[140],"analysis,":[141],"conclude":[143],"several":[144],"interesting":[145],"insights.":[146]},"counts_by_year":[{"year":2021,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
