{"id":"https://openalex.org/W4408353402","doi":"https://doi.org/10.1109/icassp49660.2025.10890358","title":"Build LLM-Based Zero-Shot Streaming TTS System with Cosyvoice","display_name":"Build LLM-Based Zero-Shot Streaming TTS System with Cosyvoice","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353402","doi":"https://doi.org/10.1109/icassp49660.2025.10890358"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890358","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890358","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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":null,"display_name":"Xiang Lyu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang Lyu","raw_affiliation_strings":["Tongyi Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongyi Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375979","display_name":"Yuxuan Wang","orcid":"https://orcid.org/0000-0002-1649-6974"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuxuan Wang","raw_affiliation_strings":["Tongyi Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongyi Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100752912","display_name":"Tianyu Zhao","orcid":"https://orcid.org/0009-0004-2935-837X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianyu Zhao","raw_affiliation_strings":["Tongyi Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongyi Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100625424","display_name":"Hao Wang","orcid":"https://orcid.org/0000-0002-7688-2236"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Wang","raw_affiliation_strings":["Tongyi Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongyi Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070862393","display_name":"Huadai Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huadai Liu","raw_affiliation_strings":["Tongyi Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongyi Lab","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001133136","display_name":"Zhihao Du","orcid":"https://orcid.org/0000-0003-3509-9322"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhihao Du","raw_affiliation_strings":["Tongyi Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongyi Lab","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.7975000143051147,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.7975000143051147,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.7886999845504761,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.7860999703407288,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.6658806800842285},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5507336258888245},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5203132629394531},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3607634902000427},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.07057076692581177}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6658806800842285},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5507336258888245},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5203132629394531},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3607634902000427},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.07057076692581177},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890358","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890358","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574"],"abstract_inverted_index":{"LLM-based":[0],"text-to-speech(TTS)":[1],"system":[2,50,95],"has":[3,63],"becoming":[4],"the":[5,59],"new":[6],"trend":[7],"and":[8,15,55,77,99],"SOTA":[9],"due":[10],"to":[11,40,45],"its":[12],"high":[13],"naturalness":[14],"zero-shot":[16,78],"capability.":[17],"However,":[18],"it":[19,68],"relies":[20],"heavily":[21],"on":[22,89],"training":[23],"data,":[24,67],"usually":[25],"requires":[26],"at":[27],"least":[28],"thousands":[29],"hours":[30,86],"of":[31],"labeled":[32],"audio.":[33],"In":[34],"this":[35],"report,":[36],"we":[37],"describe":[38],"how":[39],"use":[41],"pretrained":[42,60],"CosyVoice":[43,61],"model,":[44],"develop":[46],"a":[47],"streaming":[48],"TTS":[49,76],"which":[51,105],"supports":[52],"Indian":[53,56],"English":[54],"languages.":[57],"Though":[58],"model":[62],"never":[64],"seen":[65],"such":[66],"shows":[69,92],"good":[70],"performance":[71],"in":[72,102,108],"both":[73],"specific":[74],"speaker":[75],"voice":[79],"clone":[80],"after":[81],"finetuning":[82],"with":[83],"merely":[84],"280":[85],"data.":[87],"Experiment":[88],"LIMMITS25":[90],"challenge":[91],"that":[93],"our":[94],"achieves":[96],"4.46/4.19/4.55":[97],"naturalness,":[98],"4.29/4.34/4.27":[100],"similarity":[101],"track1/track2/track3":[103],"respectively,":[104],"ranked":[106],"1st":[107],"all":[109],"tracks.":[110]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
