论文标题
甘斯仪器：具有俯仰不变实例调理的对抗仪器声音合成
GANStrument: Adversarial Instrument Sound Synthesis with Pitch-invariant Instance Conditioning
论文作者
论文摘要
我们提出了甘斯仪器，这是一种用于仪器声合成的生成对抗模型。给定单发声音作为输入，它能够生成倾斜的仪器声音，以反映交互式时间内输入的音色。通过利用实例调节，甘施伦仪器可以实现综合声音的更好的保真度和多样性以及对各种输入的概括能力。此外，我们还为俯仰不变的特征提取器引入了对抗性训练方案，该方案可显着提高音高准确性和音色一致性。实验结果表明，甘斯仪器的表现优于强大的基准，这些基准在发电质量和输入编辑性方面不使用实例条件。定性示例可在线提供。
We propose GANStrument, a generative adversarial model for instrument sound synthesis. Given a one-shot sound as input, it is able to generate pitched instrument sounds that reflect the timbre of the input within an interactive time. By exploiting instance conditioning, GANStrument achieves better fidelity and diversity of synthesized sounds and generalization ability to various inputs. In addition, we introduce an adversarial training scheme for a pitch-invariant feature extractor that significantly improves the pitch accuracy and timbre consistency. Experimental results show that GANStrument outperforms strong baselines that do not use instance conditioning in terms of generation quality and input editability. Qualitative examples are available online.
