{"ID":2850778,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.21667","arxiv_id":"2510.21667","title":"FlowSynth: Instrument Generation Through Distributional Flow Matching and Test-Time Search","abstract":"Virtual instrument generation requires maintaining consistent timbre across different pitches and velocities, a challenge that existing note-level models struggle to address. We present FlowSynth, which combines distributional flow matching (DFM) with test-time optimization for high-quality instrument synthesis. Unlike standard flow matching that learns deterministic mappings, DFM parameterizes the velocity field as a Gaussian distribution and optimizes via negative log-likelihood, enabling the model to express uncertainty in its predictions. This probabilistic formulation allows principled test-time search: we sample multiple trajectories weighted by model confidence and select outputs that maximize timbre consistency. FlowSynth outperforms the current state-of-the-art TokenSynth baseline in both single-note quality and cross-note consistency. Our approach demonstrates that modeling predictive uncertainty in flow matching, combined with music-specific consistency objectives, provides an effective path to professional-quality virtual instruments suitable for real-time performance.","short_abstract":"Virtual instrument generation requires maintaining consistent timbre across different pitches and velocities, a challenge that existing note-level models struggle to address. We present FlowSynth, which combines distributional flow matching (DFM) with test-time optimization for high-quality instrument synthesis. Unlike...","url_abs":"https://arxiv.org/abs/2510.21667","url_pdf":"https://arxiv.org/pdf/2510.21667v1","authors":"[\"Qihui Yang\",\"Randal Leistikow\",\"Yongyi Zang\"]","published":"2025-10-24T17:24:06Z","proceeding":"cs.SD","tasks":"[\"cs.SD\"]","methods":"[]","has_code":false}