{"id":"https://openalex.org/W4296068989","doi":"https://doi.org/10.21437/interspeech.2022-10277","title":"Streamable Speech Representation Disentanglement and Multi-Level Prosody Modeling for Live One-Shot Voice Conversion","display_name":"Streamable Speech Representation Disentanglement and Multi-Level Prosody Modeling for Live One-Shot Voice Conversion","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296068989","doi":"https://doi.org/10.21437/interspeech.2022-10277"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10277","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10277","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/A5024261873","display_name":"Haoquan Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Haoquan Yang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113782870","display_name":"Liqun Deng","orcid":"https://orcid.org/0000-0002-7594-0414"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liqun Deng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083831776","display_name":"Yu Ting Yeung","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Ting Yeung","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046186949","display_name":"Nianzu Zheng","orcid":"https://orcid.org/0000-0001-6300-9684"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nianzu Zheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100359961","display_name":"Yong Xu","orcid":"https://orcid.org/0000-0003-0530-2123"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yong Xu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5024261873"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6263,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.67774421,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2578","last_page":"2582"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9976999759674072,"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":0.9976999759674072,"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":0.9804999828338623,"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/prosody","display_name":"Prosody","score":0.8546808958053589},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6532794237136841},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6104282736778259},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5775681734085083},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5319491028785706},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4474749267101288}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8546808958053589},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6532794237136841},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6104282736778259},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5775681734085083},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5319491028785706},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4474749267101288},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10277","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10277","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.75,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2579204149","https://openalex.org/W2037482962","https://openalex.org/W2395605663","https://openalex.org/W2465421051","https://openalex.org/W2005104111","https://openalex.org/W2255642176","https://openalex.org/W2358543235","https://openalex.org/W2535562660","https://openalex.org/W4296068977","https://openalex.org/W3081565196"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}
