用对抗学习和循环一致性，让音乐变调更自然且保持原唱特色。
Neurodyne: Neural Pitch Manipulation with Representation Learning and Cycle-Consistency GAN
- 通过对抗学习提取与音高无关的潜在特征，避免传统模型误分离。
- 在全局调式和模板变调任务中，合成音质更优，原声身份保留良好。
- 适合音乐制作人和音频处理研究者，尤其关注高质量变调技术。
音高调整是音乐制作中将音频片段调整至特定调式和音准的关键步骤。近年来，基于神经网络的音高调整系统因合成质量优于传统数字信号处理方法而受到青睐。然而，其性能仍受限于源-滤波器模型导致的特征解耦不准确，以及缺乏成对的调内与调外训练数据。本文提出Neurodyne，通过对抗性表示学习获得与音高无关的潜在表示，避免特征误分离；并利用循环一致性训练隐式构建成对训练数据。在全局调式和基于模板的音高调整实验中，该系统展现出优越的合成质量，同时有效保持原始演唱者身份。
原文摘要 · Abstract (English)
Pitch manipulation is the process of producers adjusting the pitch of an audio segment to a specific key and intonation, which is essential in music production. Neural-network-based pitch-manipulation systems have been popular in recent years due to their superior synthesis quality compared to classical DSP methods. However, their performance is still limited due to their inaccurate feature disentanglement using source-filter models and the lack of paired in- and out-of-tune training data. This work proposes Neurodyne to address these issues. Specifically, Neurodyne uses adversarial representation learning to learn a pitch-independent latent representation to avoid inaccurate disentanglement and cycle-consistency training to create paired training data implicitly. Experimental results on global-key and template-based pitch manipulation demonstrate the effectiveness of the proposed system, marking improved synthesis quality while maintaining the original singer identity.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。