基于扩散的音频超分辨率的推理时扩展
Inference-time Scaling for Diffusion-based Audio Super-resolution
AI总结：
本文提出一种基于扩散模型的音频超分辨率推理时扩展方法，通过验证器与搜索算法探索多条采样轨迹，在语音、音乐等任务上显著提升音质，如美学评分提升9.70%。
摘要：
扩散模型在生成任务中已展现出显著的成功，包括音频超分辨率（SR）。在电影后期制作和专辑母带处理等许多应用中，有大量的计算预算可用于实现卓越的音频质量。然而，虽然现有的扩散方法通常通过增加采样步骤来提高质量，但性能从根本上受到采样过程随机性的限制，导致输出具有高方差和质量受限。在这里，我们不是简单地增加采样步骤的数量，而是通过针对SR的推理时扩展提出了一种不同的范式，该范式在采样过程中探索多个解轨迹。我们开发了不同的任务特定验证器，并引入了两种搜索算法，包括用于SR的随机搜索和零阶搜索。通过验证器-算法组合主动引导高维解空间的探索，我们能够实现更稳健和更高质量的输出。通过在多样化的音频领域（语音、音乐、音效）和频率范围内进行广泛验证，我们展示了持续的性能提升，在语音SR从4kHz到24kHz的任务中，美学评分提高了高达9.70%，说话人相似度提高了5.88%，词错误率降低了15.20%，频谱距离降低了46.98%，展示了我们方法的有效性。音频样本可在以下网址获取：https://racerk.github.io/tt-scale-audiosr/。
英文摘要：
Diffusion models have demonstrated remarkable success in generative tasks, including audio super-resolution (SR). In many applications like movie post-production and album mastering, substantial computational budgets are available for achieving superior audio quality. However, while existing diffusion approaches typically increase sampling steps to improve quality, the performance remains fundamentally limited by the stochastic nature of the sampling process, leading to high-variance and quality-limited outputs. Here, rather than simply increasing the number of sampling steps, we propose a different paradigm through inference-time scaling for SR, which explores multiple solution trajectories during the sampling process. Different task-specific verifiers are developed, and two search algorithms, including the random search and zero-order search for SR, are introduced. By actively guiding the exploration of the high-dimensional solution space through verifier-algorithm combinations, we enable more robust and higher-quality outputs. Through extensive validation across diverse audio domains (speech, music, sound effects) and frequency ranges, we demonstrate consistent performance gains, achieving improvements of up to 9.70% in aesthetics, 5.88% in speaker similarity, 15.20% in word error rate, and 46.98% in spectral distance for speech SR from 4kHz to 24kHz, showcasing the effectiveness of our approach. Audio samples are available at: https://racerk.github.io/tt-scale-audiosr/.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
