用积分速度蒸馏实现少步语音生成，提速同时保持高质量。
IntMeanFlow: Few-step Speech Generation with Integral Velocity Distillation
- 用教师模型瞬时速度近似平均速度，避免复杂计算
- 1次采样生成频谱图，3次采样完成文本到频谱，质量不降
- 适合需要快速生成的语音合成场景，尤其部署受限环境
基于流的生成模型显著提升了文本到语音（TTS）合成质量，但推理速度受限于迭代采样和多次函数评估（NFE）。近期的MeanFlow通过建模平均速度而非瞬时速度加速生成，但在TTS中应用时面临挑战：雅可比-向量积（JVP）导致显存过高，自举训练过程不稳定。为此，我们提出IntMeanFlow框架，通过在时间区间内用教师模型的瞬时速度近似平均速度，消除对JVP和自举的需求，提升训练稳定性并降低显存占用。同时提出最优步数采样搜索（O3S）算法，自动寻找模型最优采样步数，无需额外推理开销。实验表明，IntMeanFlow可在1-NFE下完成音素到频谱生成，在3-NFE下完成文本到频谱生成，仍保持高质量合成效果。演示样本见https://vvwangvv.github.io/intmeanflow。
原文摘要 · Abstract (English)
Flow-based generative models have greatly improved text-to-speech (TTS) synthesis quality, but inference speed remains limited by the iterative sampling process and multiple function evaluations (NFE). The recent MeanFlow model accelerates generation by modeling average velocity instead of instantaneous velocity. However, its direct application to TTS encounters challenges, including GPU memory overhead from Jacobian-vector products (JVP) and training instability due to self-bootstrap processes. To address these issues, we introduce IntMeanFlow, a framework for few-step speech generation with integral velocity distillation. By approximating average velocity with the teacher's instantaneous velocity over a temporal interval, IntMeanFlow eliminates the need for JVPs and self-bootstrap, improving stability and reducing GPU memory usage. We also propose the Optimal Step Sampling Search (O3S) algorithm, which identifies the model-specific optimal sampling steps, improving speech synthesis without additional inference overhead. Experiments show that IntMeanFlow achieves 1-NFE inference for token-to-spectrogram and 3-NFE for text-to-spectrogram tasks while maintaining high-quality synthesis. Demo samples are available at https://vvwangvv.github.io/intmeanflow.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。