This paper presents FastFit, a novel neural vocoder architecture that
replaces the U-Net encoder with multiple short-time Fourier transforms (STFTs)
to achieve faster generation rates without sacrificing sample quality. We
replaced each encoder block with an STFT, with parameters equal to the temporal
resolution of each decoder block, leading to the skip connection. FastFit
reduces the number of parameters and the generation time of the model by almost
half while maintaining high fidelity. Through objective and subjective
evaluations, we demonstrated that the proposed model achieves nearly twice the
generation speed of baseline iteration-based vocoders while maintaining high
sound quality. We further showed that FastFit produces sound qualities similar
to those of other baselines in text-to-speech evaluation scenarios, including
multi-speaker and zero-shot text-to-speech.

本文介绍了一种新的神经声码器架构 FastFit, 其使用多个短时傅里叶变换 (STFT) 来替换 U-Net 编码器，从而实现更快的生成速度，而不会牺牲样品质量。通过客观和主观的评估，我们证明了该模型提高了将近两倍的基准迭代声码器的生成速度，同时保持高音质。进一步表明，在多说话人和零 - shot 文本到语音等评估场景中，FastFit 产生了与其他基线模型类似的音质。