Influenced by the field of Computer Vision, Generative Adversarial Networks (GANs) are often adopted for the audio domain using fixed-size two-dimensional spectrogram representations as the "image data". However, in the (musical) audio domain, it is often desired to generate output of variable duration. This paper presents VQCPC-GAN, an adversarial framework for synthesizing variable-length audio by exploiting Vector-Quantized Contrastive Predictive Coding (VQCPC). A sequence of VQCPC tokens extracted from real audio data serves as conditional input to a GAN architecture, providing step-wise time-dependent features of the generated content. The input noise z (characteristic in adversarial architectures) remains fixed over time, ensuring temporal consistency of global features. We evaluate the proposed model by comparing a diverse set of metrics against various strong baselines. Results show that, even though the baselines score best, VQCPC-GAN achieves comparable performance even when generating variable-length audio. Numerous sound examples are provided in the accompanying website, and we release the code for reproducibility.

中文翻译：

---

VQCPC-GAN：使用矢量量化对比预测编码的可变长度对抗性音频合成

受计算机视觉领域的影响，在音频领域通常采用生成对抗网络（GAN），以固定尺寸的二维频谱图表示形式作为“图像数据”。但是，在（音乐）音频域中，通常需要生成可变持续时间的输出。本文介绍了VQCPC-GAN，这是一种通过利用矢量量化对比预测编码（VQCPC）来合成可变长音频的对抗框架。从真实音频数据中提取的一系列VQCPC令牌用作GAN架构的条件输入，提供所生成内容的逐步时间相关特征。输入噪声z（对抗性体系结构中的特征）随时间保持不变，从而确保全局特征的时间一致性。我们通过将各种指标与各种强大的基准进行比较来评估所提出的模型。结果表明，即使基准得分最高，VQCPC-GAN甚至在生成可变长度音频时也可以达到可比的性能。随附的网站中提供了许多声音示例，并且我们发布了可重复性代码。