{"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/2505-11315","title":"Improving Inference-Time Optimisation for Vocal Effects Style Transfer with a Gaussian Prior","arxiv_id":"2505.11315","date":"2025-05-16","proceeding":null,"authors":["Chin-Yun Yu","Marco A. Martínez-Ramírez","Junghyun Koo","Wei-Hsiang Liao","Yuki Mitsufuji","György Fazekas"],"abstract":"Style Transfer with Inference-Time Optimisation (ST-ITO) is a recent approach for transferring the applied effects of a reference audio to a raw audio track. It optimises the effect parameters to minimise the distance between the style embeddings of the processed audio and the reference. However, this method treats all possible configurations equally and relies solely on the embedding space, which can lead to unrealistic or biased results. We address this pitfall by introducing a Gaussian prior derived from a vocal preset dataset, DiffVox, over the parameter space. The resulting optimisation is equivalent to maximum-a-posteriori estimation. Evaluations on vocal effects transfer on the MedleyDB dataset show significant improvements across metrics compared to baselines, including a blind audio effects estimator, nearest-neighbour approaches, and uncalibrated ST-ITO. The proposed calibration reduces parameter mean squared error by up to 33% and matches the reference style better. Subjective evaluations with 16 participants confirm our method's superiority, especially in limited data regimes. This work demonstrates how incorporating prior knowledge in inference time enhances audio effects transfer, paving the way for more effective and realistic audio processing systems.","url_abs":"https://arxiv.org/abs/2505.11315v1","url_pdf":"https://arxiv.org/pdf/2505.11315v1.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":"2505-11315","repo_url":"https://github.com/SonyResearch/diffvox","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"style-transfer","task_name":"Style Transfer"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.11315","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.11315"}},"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/SonyResearch/diffvox","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":15},"by_repo_kind":{"official":{"samples":15,"ran":0,"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":"2652eb5ac20c2d16","entry":"Roystest","repo":"SonyResearch/diffvox","repo_kind":"official","path":"utils.py","file_url":"https://github.com/SonyResearch/diffvox/blob/HEAD/utils.py","link_basis":"harvester_set","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":"2652eb5ac20c2d16"}},{"code_sha256_prefix":"3663a37429d33025","entry":"ShaWilstat","repo":"SonyResearch/diffvox","repo_kind":"official","path":"utils.py","file_url":"https://github.com/SonyResearch/diffvox/blob/HEAD/utils.py","link_basis":"harvester_set","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":"3663a37429d33025"}},{"code_sha256_prefix":"c9d68638ae695f53","entry":"broadcast2stereo","repo":"SonyResearch/diffvox","repo_kind":"official","path":"modules/fx.py","file_url":"https://github.com/SonyResearch/diffvox/blob/HEAD/modules/fx.py","link_basis":"harvester_set","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":"c9d68638ae695f53"}},{"code_sha256_prefix":"8924ff4f9ca3024c","entry":"eig_22","repo":"SonyResearch/diffvox","repo_kind":"official","path":"modules/functional.py","file_url":"https://github.com/SonyResearch/diffvox/blob/HEAD/modules/functional.py","link_basis":"harvester_set","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":"8924ff4f9ca3024c"}},{"code_sha256_prefix":"c38f1e6f404f3fdd","entry":"fir","repo":"SonyResearch/diffvox","repo_kind":"official","path":"modules/functional.py","file_url":"https://github.com/SonyResearch/diffvox/blob/HEAD/modules/functional.py","link_basis":"harvester_set","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":"c38f1e6f404f3fdd"}},{"code_sha256_prefix":"6565cfd9b49e27c7","entry":"get_chunks","repo":"SonyResearch/diffvox","repo_kind":"official","path":"modules/utils.py","file_url":"https://github.com/SonyResearch/diffvox/blob/HEAD/modules/utils.py","link_basis":"harvester_set","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":"6565cfd9b49e27c7"}},{"code_sha256_prefix":"3740de98f405734a","entry":"get_reference_query_chunks","repo":"SonyResearch/diffvox","repo_kind":"official","path":"ito.py","file_url":"https://github.com/SonyResearch/diffvox/blob/HEAD/ito.py","link_basis":"harvester_set","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":"3740de98f405734a"}},{"code_sha256_prefix":"f30be0c135e88956","entry":"inv_22","repo":"SonyResearch/diffvox","repo_kind":"official","path":"modules/functional.py","file_url":"https://github.com/SonyResearch/diffvox/blob/HEAD/modules/functional.py","link_basis":"harvester_set","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":"f30be0c135e88956"}},{"code_sha256_prefix":"f922b72b0b6b60d9","entry":"logp_y_given_x","repo":"SonyResearch/diffvox","repo_kind":"official","path":"ito.py","file_url":"https://github.com/SonyResearch/diffvox/blob/HEAD/ito.py","link_basis":"harvester_set","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":"f922b72b0b6b60d9"}},{"code_sha256_prefix":"decc18ed8ab0182d","entry":"module2coeffs","repo":"SonyResearch/diffvox","repo_kind":"official","path":"modules/fx.py","file_url":"https://github.com/SonyResearch/diffvox/blob/HEAD/modules/fx.py","link_basis":"harvester_set","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":"decc18ed8ab0182d"}},{"code_sha256_prefix":"13c5b070ee7dafbe","entry":"one_evaluation","repo":"SonyResearch/diffvox","repo_kind":"official","path":"ito.py","file_url":"https://github.com/SonyResearch/diffvox/blob/HEAD/ito.py","link_basis":"harvester_set","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":"13c5b070ee7dafbe"}},{"code_sha256_prefix":"29a2143844456a16","entry":"remove_fx_parametrisation","repo":"SonyResearch/diffvox","repo_kind":"official","path":"modules/utils.py","file_url":"https://github.com/SonyResearch/diffvox/blob/HEAD/modules/utils.py","link_basis":"harvester_set","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":"29a2143844456a16"}},{"code_sha256_prefix":"3eab58f0952ec755","entry":"rt_delay","repo":"SonyResearch/diffvox","repo_kind":"official","path":"modules/rt.py","file_url":"https://github.com/SonyResearch/diffvox/blob/HEAD/modules/rt.py","link_basis":"harvester_set","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":"3eab58f0952ec755"}},{"code_sha256_prefix":"65fa53f078ce4c6f","entry":"rt_fdn","repo":"SonyResearch/diffvox","repo_kind":"official","path":"modules/rt.py","file_url":"https://github.com/SonyResearch/diffvox/blob/HEAD/modules/rt.py","link_basis":"harvester_set","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":"65fa53f078ce4c6f"}},{"code_sha256_prefix":"6e6dd311d8f31c90","entry":"vec2statedict","repo":"SonyResearch/diffvox","repo_kind":"official","path":"modules/utils.py","file_url":"https://github.com/SonyResearch/diffvox/blob/HEAD/modules/utils.py","link_basis":"harvester_set","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":"6e6dd311d8f31c90"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}