{"ID":6536495,"CreatedAt":"2026-07-14T01:21:01.169441415Z","UpdatedAt":"2026-07-14T17:47:10.356190764Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.10421","arxiv_id":"2607.10421","title":"FdAudio: MeanFlow-Anchored Fréchet-Distance Post-Training for One-Step Text-to-Audio Generation","abstract":"While recent few-step sampling text-to-audio generation models like MeanAudio substantially accelerate generation by modeling average velocities, their strict one-step generation quality still lags significantly behind multi-step counterparts. We propose FdAudio to bridge this gap. Unlike MeanAudio, which relies solely on regression against target velocity fields, our post-training approach optimizes the final one-step distribution directly across pre-trained embedding spaces via a multi-representation Fréchet-distance (FD) loss. Crucially, to prevent the multi-step degradation that naive post-training with FD-loss causes, we introduce a MeanFlow consistency objective as a structural anchor. Results demonstrate that FdAudio establishes state-of-the-art one-step T2A generation quality among few-step systems, yielding an 11.4% reduction in FD score and a 28.8% improvement in FAD score relative to the baseline MeanAudio framework. Notably, we solve FD post-training's naive multi-step degradation issue by proposing the MeanFlow anchor, enabling a 25-step sampling path to maintain high-fidelity audio synthesis that matches or surpasses strong multi-step models at a fraction of their computational latency.","short_abstract":"While recent few-step sampling text-to-audio generation models like MeanAudio substantially accelerate generation by modeling average velocities, their strict one-step generation quality still lags significantly behind multi-step counterparts. We propose FdAudio to bridge this gap. Unlike MeanAudio, which relies solely...","url_abs":"https://arxiv.org/abs/2607.10421","url_pdf":"https://arxiv.org/pdf/2607.10421v1","authors":"[\"Kuan-Po Huang\",\"Bo-Ru Lu\",\"Ho-Lam Chung\",\"Shih-Hsin Wang\",\"Hung-yi Lee\"]","published":"2026-07-11T17:59:32Z","proceeding":"eess.AS","tasks":"[\"eess.AS\",\"cs.SD\"]","methods":"[]","has_code":false}