Time series generation (TSG) studies have mainly focused on the use of Generative Adversarial Networks (GANs) combined with recurrent neural network (RNN) variants. However, the fundamental limitations and challenges of training GANs still remain. In addition, the RNN-family typically has difficulties with temporal consistency between distant timesteps. Motivated by the successes in the image generation (IMG) domain, we propose TimeVQVAE, the first work, to our knowledge, that uses vector quantization (VQ) techniques to address the TSG problem. Moreover, the priors of the discrete latent spaces are learned with bidirectional transformer models that can better capture global temporal consistency. We also propose VQ modeling in a time-frequency domain, separated into low-frequency (LF) and high-frequency (HF). This allows us to retain important characteristics of the time series and, in turn, generate new synthetic signals that are of better quality, with sharper changes in modularity, than its competing TSG methods. Our experimental evaluation is conducted on all datasets from the UCR archive, using well-established metrics in the IMG literature, such as Fr\'echet inception distance and inception scores. Our implementation on GitHub: \url{https://github.com/ML4ITS/TimeVQVAE}.

翻译：时间序列生成（TSG）研究主要集中于将生成对抗网络（GAN）与循环神经网络（RNN）变体相结合。然而，训练GAN的根本性局限和挑战仍然存在。此外，RNN系列模型通常难以处理远时间步长之间的时间一致性。受图像生成（IMG）领域成功案例的启发，我们提出了TimeVQVAE——据我们所知，这是首个利用向量量化（VQ）技术解决时间序列生成问题的工作。同时，我们通过双向Transformer模型学习离散潜在空间的先验分布，从而更好地捕捉全局时间一致性。我们还提出了时频域中的VQ建模方法，将信号分为低频（LF）和高频（HF）分量。这使得我们能够保留时间序列的重要特征，进而生成质量更高的合成信号，其模态变化比现有TSG方法更为锐利。我们在UCR存档所有数据集上进行了实验评估，采用图像生成文献中成熟的度量指标，如Fréchet起始距离和起始分数。我们的代码实现已在GitHub上开源：\url{https://github.com/ML4ITS/TimeVQVAE}。