{"id":"https://openalex.org/W4385822410","doi":"https://doi.org/10.21437/interspeech.2023-2558","title":"Cross-utterance Conditioned Coherent Speech Editing","display_name":"Cross-utterance Conditioned Coherent Speech Editing","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385822410","doi":"https://doi.org/10.21437/interspeech.2023-2558"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-2558","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-2558","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://discovery.ucl.ac.uk/10178175/7/Wang_yu23d_interspeech.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100622629","display_name":"Yu Cheng","orcid":"https://orcid.org/0000-0003-4258-0499"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108048308","display_name":"Yang Li","orcid":"https://orcid.org/0009-0008-5830-9306"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059080410","display_name":"Weiqin Zu","orcid":"https://orcid.org/0009-0002-9745-4457"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weiqin Zu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063874810","display_name":"Fanglei Sun","orcid":"https://orcid.org/0000-0002-4302-2512"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fanglei Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101846140","display_name":"Tian Zheng","orcid":"https://orcid.org/0000-0003-0379-7986"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng Tian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100384769","display_name":"Jun Wang","orcid":"https://orcid.org/0000-0002-6005-2545"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Wang","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":0.2178,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.43294786,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2108","last_page":"2112"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9879999756813049,"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":0.9879999756813049,"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":0.9546999931335449,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9413999915122986,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8005045652389526},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6915209293365479},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5298193693161011},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36267685890197754}],"concepts":[{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.8005045652389526},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6915209293365479},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5298193693161011},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36267685890197754}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2023-2558","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-2558","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:10178175","is_oa":true,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/10178175/","pdf_url":"https://discovery.ucl.ac.uk/10178175/7/Wang_yu23d_interspeech.pdf","source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. (pp. pp. 2108-2112). ISCA: Dublin, Ireland. (2023)","raw_type":"Proceedings paper"}],"best_oa_location":{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:10178175","is_oa":true,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/10178175/","pdf_url":"https://discovery.ucl.ac.uk/10178175/7/Wang_yu23d_interspeech.pdf","source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. (pp. pp. 2108-2112). ISCA: Dublin, Ireland. (2023)","raw_type":"Proceedings paper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4385822410.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W2333799855","https://openalex.org/W2351687372"],"abstract_inverted_index":{"Text-based":[0],"speech":[1,11,59,79,97],"editing":[2,18,80,128],"systems":[3,19],"are":[4],"developed":[5],"to":[6,9,38,47,63],"enable":[7],"users":[8],"modify":[10],"based":[12,20],"on":[13,21,114,126],"the":[14,48,51,57,65,85,89,106,109,124],"transcript.":[15],"Existing":[16],"state-of-the-art":[17],"neural":[22],"networks":[23],"do":[24],"partial":[25],"inferences":[26],"with":[27,56],"no":[28],"exception,":[29],"that":[30,36,82,120],"is,":[31],"only":[32],"generate":[33,96],"new":[34],"words":[35],"need":[37],"be":[39],"replaced":[40],"or":[41],"inserted.":[42],"This":[43],"manner":[44],"usually":[45],"leads":[46],"prosody":[49,133],"of":[50,67],"edited":[52],"part":[53],"being":[54],"inconsistent":[55],"surrounding":[58],"and":[60,105,116,132],"a":[61,75],"failure":[62],"handle":[64],"alteration":[66],"intonation.":[68],"To":[69],"address":[70],"these":[71],"problems,":[72],"we":[73],"propose":[74],"cross-utterance":[76],"conditioned":[77],"coherent":[78],"system,":[81],"first":[83],"does":[84],"entire":[86],"reasoning":[87],"at":[88],"inference":[90],"time.":[91],"Our":[92],"proposed":[93],"system":[94],"can":[95],"by":[98],"utilizing":[99],"speaker":[100],"information,":[101],"context,":[102],"acoustic":[103],"features,":[104],"mel-spectrogram":[107],"from":[108],"original":[110],"audio.":[111],"Experiments":[112],"conducted":[113],"subjective":[115],"objective":[117],"metrics":[118],"demonstrate":[119],"our":[121],"approach":[122],"outperforms":[123],"baseline":[125],"various":[127],"operations":[129],"regarding":[130],"naturalness":[131],"consistency.":[134]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}