{"id":"https://openalex.org/W4414691940","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1928","title":"ZipVoice-Dialog: Non-Autoregressive Spoken Dialogue Generation with Flow Matching","display_name":"ZipVoice-Dialog: Non-Autoregressive Spoken Dialogue Generation with Flow Matching","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4414691940","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1928"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1928","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1928","pdf_url":"https://aclanthology.org/2026.findings-acl.1928.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.1928.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063667378","display_name":"Zhu Han","orcid":"https://orcid.org/0000-0002-6606-5822"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Zhu","raw_affiliation_strings":["Xiaomi Corp. , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corp. , Beijing , China","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068307574","display_name":"Wei Kang","orcid":"https://orcid.org/0000-0003-0193-2654"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Kang","raw_affiliation_strings":["Xiaomi Corp. , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corp. , Beijing , China","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102707172","display_name":"Liyong Guo","orcid":"https://orcid.org/0009-0002-2465-3914"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liyong Guo","raw_affiliation_strings":["Xiaomi Corp. , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corp. , Beijing , China","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066643565","display_name":"Zengwei Yao","orcid":"https://orcid.org/0000-0002-2331-2387"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zengwei Yao","raw_affiliation_strings":["Xiaomi Corp. , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corp. , Beijing , China","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040568268","display_name":"Fangjun Kuang","orcid":null},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangjun Kuang","raw_affiliation_strings":["Xiaomi Corp. , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corp. , Beijing , China","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113987256","display_name":"Weiji Zhuang","orcid":null},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiji Zhuang","raw_affiliation_strings":["Xiaomi Corp. , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corp. , Beijing , China","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101675943","display_name":"Zhaoqing Li","orcid":"https://orcid.org/0009-0002-5504-7802"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaoqing Li","raw_affiliation_strings":["Xiaomi Corp. , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corp. , Beijing , China","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101865808","display_name":"Zhifeng Han","orcid":"https://orcid.org/0000-0002-7493-4530"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhifeng Han","raw_affiliation_strings":["Xiaomi Corp. , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corp. , Beijing , China","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100366067","display_name":"Dong Zhang","orcid":"https://orcid.org/0000-0001-6756-6664"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Zhang","raw_affiliation_strings":["Xiaomi Corp. , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corp. , Beijing , China","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100339882","display_name":"Xin Zhang","orcid":"https://orcid.org/0000-0003-0394-7972"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Zhang","raw_affiliation_strings":["Xiaomi Corp. , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corp. , Beijing , China","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074833963","display_name":"Xingchen Song","orcid":"https://orcid.org/0009-0009-9516-5361"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingchen Song","raw_affiliation_strings":["Xiaomi Corp. , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corp. , Beijing , China","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lingxuan Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingxuan Ye","raw_affiliation_strings":["Xiaomi Corp. , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corp. , Beijing , China","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Long Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Lin","raw_affiliation_strings":["Xiaomi Corp. , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corp. , Beijing , China","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084286453","display_name":"Daniel Povey","orcid":"https://orcid.org/0000-0002-0611-3634"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daniel Povey","raw_affiliation_strings":["Xiaomi Corp. , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corp. , Beijing , China","institution_ids":["https://openalex.org/I862669128"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I862669128"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00751104,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"38717","last_page":"38729"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9919000267982483,"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/T10028","display_name":"Topic Modeling","score":0.9919000267982483,"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/T12031","display_name":"Speech and dialogue systems","score":0.9805999994277954,"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/T12128","display_name":"AI in Service Interactions","score":0.9258000254631042,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.6158999800682068},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5860999822616577},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5623999834060669},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5273000001907349},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.44769999384880066},{"id":"https://openalex.org/keywords/structured-prediction","display_name":"Structured prediction","score":0.35109999775886536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8102999925613403},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.6158999800682068},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5860999822616577},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5623999834060669},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5446000099182129},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5411999821662903},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5351999998092651},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5273000001907349},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.44769999384880066},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.35109999775886536},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C504583287","wikidata":"https://www.wikidata.org/wiki/Q1428637","display_name":"Spoken word","level":3,"score":0.25850000977516174}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1928","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1928","pdf_url":"https://aclanthology.org/2026.findings-acl.1928.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.09318","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2507.09318","pdf_url":"https://arxiv.org/pdf/2507.09318","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.09318","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.09318","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.1928","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1928","pdf_url":"https://aclanthology.org/2026.findings-acl.1928.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414691940.pdf","grobid_xml":"https://content.openalex.org/works/W4414691940.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Han":[0],"Zhu,":[1],"Wei":[2],"Kang,":[3],"Liyong":[4],"Guo,":[5],"Zengwei":[6],"Yao,":[7],"Fangjun":[8],"Kuang,":[9],"Weiji":[10],"Zhuang,":[11],"Zhaoqing":[12],"Li,":[13],"Zhifeng":[14],"Han,":[15],"Dong":[16],"Zhang,":[17,19],"Xin":[18],"Xingchen":[20],"Song,":[21],"Lingxuan":[22],"Ye,":[23],"Long":[24],"Lin,":[25],"Daniel":[26],"Povey.":[27],"Findings":[28],"of":[29],"the":[30],"Association":[31],"for":[32],"Computational":[33],"Linguistics:":[34],"ACL":[35],"2026.":[36,37]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}
