Neural vocoders often struggle with aliasing in latent feature spaces, caused by time-domain nonlinear operations and resampling layers. Aliasing folds high-frequency components into the low-frequency range, making aliased and original frequency components indistinguishable and introducing two practical issues. First, aliasing complicates the waveform generation process, as the subsequent layers must address these aliasing effects, increasing the computational complexity. Second, it limits extrapolation performance, particularly in handling high fundamental frequencies, which degrades the perceptual quality of generated speech waveforms. This paper demonstrates that 1) time-domain nonlinear operations inevitably introduce aliasing but provide a strong inductive bias for harmonic generation, and 2) time-frequency-domain processing can achieve aliasing-free waveform synthesis but lacks the inductive bias for effective harmonic generation. Building on this insight, we propose Wavehax, an aliasing-free neural WAVEform generator that integrates 2D convolution and a HArmonic prior for reliable Complex Spectrogram estimation. Experimental results show that Wavehax achieves speech quality comparable to existing high-fidelity neural vocoders and exhibits exceptional robustness in scenarios requiring high fundamental frequency extrapolation, where aliasing effects become typically severe. Moreover, Wavehax requires less than 5% of the multiply-accumulate operations and model parameters compared to HiFi-GAN V1, while achieving over four times faster CPU inference speed.

翻译：神经声码器常因时域非线性操作与重采样层而在潜在特征空间中产生混叠现象。混叠将高频分量折叠至低频范围，使得混叠频率分量与原始频率分量无法区分，并引发两个实际问题：首先，混叠使波形生成过程复杂化，后续网络层必须处理这些混叠效应，从而增加计算复杂度；其次，混叠限制了外推性能，尤其在处理高基频时，会降低生成语音波形的感知质量。本文论证了：1）时域非线性操作虽不可避免地引入混叠，但为谐波生成提供了强归纳偏置；2）时频域处理可实现无混叠波形合成，但缺乏有效谐波生成的归纳偏置。基于此洞见，我们提出Wavehax——一种集成二维卷积与谐波先验的无混叠神经波形生成器，用于实现可靠的复数谱估计。实验结果表明，Wavehax在语音质量上可与现有高保真神经声码器相媲美，并在需要高基频外推（混叠效应通常尤为严重）的场景中展现出卓越的鲁棒性。此外，与HiFi-GAN V1相比，Wavehax仅需不足5%的乘累加运算量与模型参数量，同时实现了四倍以上的CPU推理加速。