{"id":"https://openalex.org/W7140140802","doi":"https://doi.org/10.48550/arxiv.2603.19798","title":"Borderless Long Speech Synthesis","display_name":"Borderless Long Speech Synthesis","publication_year":2026,"publication_date":"2026-03-20","ids":{"openalex":"https://openalex.org/W7140140802","doi":"https://doi.org/10.48550/arxiv.2603.19798"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2603.19798","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.19798","pdf_url":"https://arxiv.org/pdf/2603.19798","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,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2603.19798","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074833963","display_name":"Xingchen Song","orcid":"https://orcid.org/0009-0009-9516-5361","observed_orcids":["https://orcid.org/0009-0009-9516-5361"]},"institutions":[{"id":"https://openalex.org/I4210125222","display_name":"WNET (United States)","ror":"https://ror.org/0296jvb66","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125222"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Song, Xingchen","raw_affiliation_strings":["MiLM Plus , Xiaomi Inc. , China","WeNet Open Source Community"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MiLM Plus , Xiaomi Inc. , China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"WeNet Open Source Community","institution_ids":["https://openalex.org/I4210125222"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130411653","display_name":"Di Wu","orcid":"https://orcid.org/0009-0000-3766-2620","observed_orcids":["https://orcid.org/0009-0000-3766-2620"]},"institutions":[{"id":"https://openalex.org/I4210125222","display_name":"WNET (United States)","ror":"https://ror.org/0296jvb66","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125222"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Wu, Di","raw_affiliation_strings":["MiLM Plus , Xiaomi Inc. , China","WeNet Open Source Community"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MiLM Plus , Xiaomi Inc. , China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"WeNet Open Source Community","institution_ids":["https://openalex.org/I4210125222"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002904368","display_name":"Dinghao Zhou","orcid":"https://orcid.org/0009-0000-8519-4630","observed_orcids":["https://orcid.org/0009-0000-8519-4630"]},"institutions":[{"id":"https://openalex.org/I4210125222","display_name":"WNET (United States)","ror":"https://ror.org/0296jvb66","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125222"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Zhou, Dinghao","raw_affiliation_strings":["MiLM Plus , Xiaomi Inc. , China","WeNet Open Source Community"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MiLM Plus , Xiaomi Inc. , China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"WeNet Open Source Community","institution_ids":["https://openalex.org/I4210125222"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128902934","display_name":"Pengyu Cheng","orcid":null,"observed_orcids":[]},"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":"Cheng, Pengyu","raw_affiliation_strings":["MiLM Plus , Xiaomi Inc. , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MiLM Plus , Xiaomi Inc. , China","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113430879","display_name":"Hongwu Ding","orcid":null,"observed_orcids":[]},"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":"Ding, Hongwu","raw_affiliation_strings":["MiLM Plus , Xiaomi Inc. , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MiLM Plus , Xiaomi Inc. , China","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059090577","display_name":"Yunchao He","orcid":null,"observed_orcids":[]},"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":"He, Yunchao","raw_affiliation_strings":["MiLM Plus , Xiaomi Inc. , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MiLM Plus , Xiaomi Inc. , China","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130369299","display_name":"Jie Wang","orcid":"https://orcid.org/0000-0003-0380-6395","observed_orcids":["https://orcid.org/0000-0003-0380-6395"]},"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":"Wang, Jie","raw_affiliation_strings":["MiLM Plus , Xiaomi Inc. , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MiLM Plus , Xiaomi Inc. , China","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116594429","display_name":"Shengfan Shen","orcid":null,"observed_orcids":[]},"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"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shen, Shengfan","raw_affiliation_strings":["MiLM Plus , Xiaomi Inc. , China","Nanjing University , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MiLM Plus , Xiaomi Inc. , China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Nanjing University , China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130392220","display_name":"Sixiang Lv","orcid":null,"observed_orcids":[]},"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"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lv, Sixiang","raw_affiliation_strings":["MiLM Plus , Xiaomi Inc. , China","Nanjing University , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MiLM Plus , Xiaomi Inc. , China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Nanjing University , China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073616755","display_name":"Lichun Fan","orcid":"https://orcid.org/0009-0008-8153-8887","observed_orcids":["https://orcid.org/0009-0008-8153-8887"]},"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":"Fan, Lichun","raw_affiliation_strings":["MiLM Plus , Xiaomi Inc. , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MiLM Plus , Xiaomi Inc. , China","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130328359","display_name":"Hang Su","orcid":null,"observed_orcids":[]},"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":"Su, Hang","raw_affiliation_strings":["MiLM Plus , Xiaomi Inc. , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MiLM Plus , Xiaomi Inc. , China","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130365716","display_name":"Yifeng Wang","orcid":null,"observed_orcids":[]},"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":"Wang, Yifeng","raw_affiliation_strings":["MiLM Plus , Xiaomi Inc. , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MiLM Plus , Xiaomi Inc. , China","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130382146","display_name":"Shuai Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Shuai","raw_affiliation_strings":["Nanjing University , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University , China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130352827","display_name":"Meng Meng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng, Meng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5054843960","display_name":"Jian Luan","orcid":"https://orcid.org/0000-0002-2383-226X","observed_orcids":["https://orcid.org/0000-0002-2383-226X"]},"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":"Luan, Jian","raw_affiliation_strings":["MiLM Plus , Xiaomi Inc. , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MiLM Plus , Xiaomi Inc. , China","institution_ids":["https://openalex.org/I862669128"]}]}],"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":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":0.9994999766349792,"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":0.9994999766349792,"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":0.00019999999494757503,"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":9.999999747378752e-05,"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/text-to-speech","display_name":"text-to-speech","score":0.9210000038146973},{"id":"https://openalex.org/keywords/multi-speaker-speech-synthesis","display_name":"multi-speaker speech synthesis","score":0.8690000176429749},{"id":"https://openalex.org/keywords/llm-based-agents","display_name":"LLM agents","score":0.6949999928474426},{"id":"https://openalex.org/keywords/chain-of-thought-reasoning","display_name":"chain-of-thought reasoning","score":0.8429999947547913},{"id":"https://openalex.org/keywords/instruction-following","display_name":"instruction following","score":0.6119999885559082},{"id":"https://openalex.org/keywords/voice-design","display_name":"voice design","score":0.42100000381469727},{"id":"https://openalex.org/keywords/annotation-scheme","display_name":"annotation scheme","score":0.6729999780654907},{"id":"https://openalex.org/keywords/paralinguistic-cues","display_name":"paralinguistic cues","score":0.7760000228881836},{"id":"https://openalex.org/keywords/overlapping-speech","display_name":"overlapping speech","score":0.4169999957084656},{"id":"https://openalex.org/keywords/emotional-speech-synthesis","display_name":"emotional speech synthesis","score":0.5429999828338623}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7810999751091003},{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.6481000185012817},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5228999853134155},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4749999940395355},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4731999933719635},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4569999873638153},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.44209998846054077},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4180000126361847},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.40799999237060547},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39890000224113464},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.3919999897480011},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.38280001282691956},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.3686000108718872},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3463999927043915},{"id":"https://openalex.org/C130727458","wikidata":"https://www.wikidata.org/wiki/Q1639109","display_name":"Coarticulation","level":3,"score":0.27869999408721924},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.26969999074935913},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.26759999990463257},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.2635999917984009},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.26330000162124634}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2603.19798","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.19798","pdf_url":"https://arxiv.org/pdf/2603.19798","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,"listed_in":[],"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.2603.19798","doi":"https://doi.org/10.48550/arxiv.2603.19798","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.19798","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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2603.19798","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.19798","pdf_url":"https://arxiv.org/pdf/2603.19798","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,"listed_in":[],"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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140140802.pdf","grobid_xml":"https://content.openalex.org/works/W7140140802.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7165141801","https://openalex.org/W7171535284","https://openalex.org/W7083693352","https://openalex.org/W7117158752","https://openalex.org/W7161716687","https://openalex.org/W7165636779","https://openalex.org/W4416045834","https://openalex.org/W7140086187","https://openalex.org/W7203614717","https://openalex.org/W2475086279"],"abstract_inverted_index":{"Most":[0],"existing":[1],"text-to-speech":[2],"(TTS)":[3],"systems":[4],"either":[5],"synthesize":[6],"speech":[7,222],"sentence":[8,10],"by":[9,158],"and":[11,53,93,108,130,173],"stitch":[12],"the":[13,59,78,98,119,153,160,170,174,215],"results":[14],"together,":[15],"or":[16,33],"drive":[17],"synthesis":[18,175],"from":[19,185,217],"plain-text":[20],"dialogues":[21],"alone.":[22],"Both":[23],"approaches":[24],"leave":[25],"models":[26],"with":[27,126,136],"little":[28],"understanding":[29],"of":[30,140,207],"global":[31],"context":[32],"paralinguistic":[34],"cues,":[35],"making":[36],"it":[37],"hard":[38],"to":[39,189,204,219],"capture":[40],"real-world":[41],"phenomena":[42],"such":[43],"as":[44,82,164],"multi-speaker":[45,89],"interactions":[46],"(interruptions,":[47],"overlapping":[48],"speech),":[49],"evolving":[50],"emotional":[51],"arcs,":[52],"varied":[54],"acoustic":[55],"environments.":[56],"We":[57,149],"introduce":[58],"Borderless":[60],"Long":[61],"Speech":[62],"Synthesis":[63],"framework":[64],"for":[65],"agent-centric,":[66],"borderless":[67,220],"long":[68,221],"audio":[69],"synthesis.":[70,96,223],"Rather":[71],"than":[72],"targeting":[73],"a":[74,83,103,110,124,127,165,178,201],"single":[75],"narrow":[76],"task,":[77],"system":[79,154],"is":[80,155],"designed":[81],"unified":[84],"capability":[85],"set":[86],"spanning":[87],"VoiceDesigner,":[88],"synthesis,":[90],"Instruct":[91],"TTS,":[92],"long-form":[94],"text":[95],"On":[97,118],"data":[99],"side,":[100,121],"we":[101,115,122],"propose":[102],"\"Labeling":[104],"over":[105],"filtering/cleaning\"":[106],"strategy":[107],"design":[109],"top-down,":[111],"multi-level":[112],"annotation":[113,162],"schema":[114],"call":[116],"Global-Sentence-Token.":[117],"model":[120],"adopt":[123],"backbone":[125],"continuous":[128],"tokenizer":[129],"add":[131],"Chain-of-Thought":[132],"(CoT)":[133],"reasoning":[134],"together":[135],"Dimension":[137],"Dropout,":[138],"both":[139],"which":[141],"markedly":[142],"improve":[143],"instruction":[144],"following":[145],"under":[146],"complex":[147],"conditions.":[148],"further":[150],"show":[151],"that":[152,183],"Native":[156],"Agentic":[157],"design:":[159],"hierarchical":[161],"doubles":[163],"Structured":[166],"Semantic":[167],"Interface":[168],"between":[169],"LLM":[171,203],"Agent":[172],"engine,":[176],"creating":[177],"layered":[179],"control":[180,198],"protocol":[181],"stack":[182],"spans":[184],"scene":[186],"semantics":[187],"down":[188],"phonetic":[190],"detail.":[191],"Text":[192],"thereby":[193],"becomes":[194],"an":[195],"information-complete,":[196],"wide-band":[197],"channel,":[199],"enabling":[200],"front-end":[202],"convert":[205],"inputs":[206],"any":[208],"modality":[209],"into":[210],"structured":[211],"generation":[212],"commands,":[213],"extending":[214],"paradigm":[216],"Text2Speech":[218]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-03-24T00:00:00"}
