{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/prompt-singer-controllable-singing-voice","title":"Prompt-Singer: Controllable Singing-Voice-Synthesis with Natural Language Prompt","arxiv_id":"2403.11780","date":"2024-03-18","proceeding":null,"authors":["Yongqi Wang","Ruofan Hu","Rongjie Huang","Zhiqing Hong","RuiQi Li","Wenrui Liu","Fuming You","Tao Jin","Zhou Zhao"],"abstract":"Recent singing-voice-synthesis (SVS) methods have achieved remarkable audio quality and naturalness, yet they lack the capability to control the style attributes of the synthesized singing explicitly. We propose Prompt-Singer, the first SVS method that enables attribute controlling on singer gender, vocal range and volume with natural language. We adopt a model architecture based on a decoder-only transformer with a multi-scale hierarchy, and design a range-melody decoupled pitch representation that enables text-conditioned vocal range control while keeping melodic accuracy. Furthermore, we explore various experiment settings, including different types of text representations, text encoder fine-tuning, and introducing speech data to alleviate data scarcity, aiming to facilitate further research. Experiments show that our model achieves favorable controlling ability and audio quality. Audio samples are available at http://prompt-singer.github.io .","url_abs":"https://arxiv.org/abs/2403.11780v3","url_pdf":"https://arxiv.org/pdf/2403.11780v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"prompt-singer-controllable-singing-voice","repo_url":"https://github.com/cyanbx/Prompt-Singer","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"singing-voice-synthesis","task_name":"Singing Voice Synthesis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2403.11780","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.11780"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cyanbx/Prompt-Singer","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/mozillazg/python-pinyin","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"unverified":3},"by_repo_kind":{"official":{"samples":5,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"65f934060caf4ad9","entry":"Snake","repo":"cyanbx/Prompt-Singer","repo_kind":"official","path":"wave_generation/models.py","file_url":"https://github.com/cyanbx/Prompt-Singer/blob/HEAD/wave_generation/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"65f934060caf4ad9"}},{"code_sha256_prefix":"6a471142204736fb","entry":"SnakeBeta","repo":"cyanbx/Prompt-Singer","repo_kind":"official","path":"wave_generation/models.py","file_url":"https://github.com/cyanbx/Prompt-Singer/blob/HEAD/wave_generation/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6a471142204736fb"}},{"code_sha256_prefix":"3fe92788a5d11a8b","entry":"AMPBlock1","repo":"cyanbx/Prompt-Singer","repo_kind":"official","path":"wave_generation/models.py","file_url":"https://github.com/cyanbx/Prompt-Singer/blob/HEAD/wave_generation/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3fe92788a5d11a8b"}},{"code_sha256_prefix":"3e277320de011dd8","entry":"AMPBlock2","repo":"cyanbx/Prompt-Singer","repo_kind":"official","path":"wave_generation/models.py","file_url":"https://github.com/cyanbx/Prompt-Singer/blob/HEAD/wave_generation/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3e277320de011dd8"}},{"code_sha256_prefix":"a3d8166f1f960f23","entry":"BigVGAN","repo":"cyanbx/Prompt-Singer","repo_kind":"official","path":"wave_generation/models.py","file_url":"https://github.com/cyanbx/Prompt-Singer/blob/HEAD/wave_generation/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a3d8166f1f960f23"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}