二次差音频谱的学习连续合成
Learned Continuous Synthesis of Quadratic Difference Tone Spectra
- Universitat Pompeu Fabra（庞培法布拉大学）
- University of Birmingham（伯明翰大学）
- Pontificia Universidad Católica de Chile（智利天主教大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出一种基于神经网络的连续合成方法，学习二次差音频谱的逆映射，解决先前数值方法的不连续和难控制问题，并实现实时版本，适用于音乐应用。
AI中文摘要：
二次差音（QDT）是听觉失真产物的一种，其中一种“幻影”纯音虽不存在于声学信号中，但听众却能清晰听到。利用这一现象，可以为音乐目的合成谐波丰富的音调，这种技术称为二次差音频谱（QDTS）合成。先前的工作引入了基于失真函数的数值方法来合成QDTS，该函数将目标QDTS与泛音结构的载波信号联系起来。虽然这些方法准确，但它们是随机且不连续的，这使得它们难以用于音乐控制，并且实际上仅限于平稳信号。本文提出了一种基于神经网络的方法，在类似自编码器的配置中学习失真映射的近似逆，产生连续近似，解决了先前的局限性。实验结果表明，尽管数值精度略低，但该方法足以满足感知和音乐应用。我们还用Max实现了一个实时版本并评估其性能。各种声音示例展示了其表现力和音乐潜力。随附的源代码、音频示例、教程和软件可在https URL获取。
英文摘要：
Quadratic difference tones (QDTs) are a species of auditory distortion product in which a "phantom" pure tone, absent from the acoustic signal, is clearly audible to listeners. Exploiting this phenomenon, one can synthesize harmonically rich tones for musical purposes, a technique called Quadratic Difference Tone Spectrum (QDTS) synthesis. Previous works have introduced numerical methods to synthesize QDTS based on the distortion function, which links a target QDTS and an overtone-structured carrier signal. While accurate, these methods were stochastic and discontinuous, making them difficult to control for musical purposes and effectively limiting them to stationary signals. This paper proposes a neural network-based approach that learns an approximate inverse of the distortion mapping in an autoencoder-like configuration, producing a continuous approximation that addresses prior limitations. Experimental results show that, although slightly less numerically precise, the method is sufficient for perceptual and musical applications. We also implement a real-time version in Max and evaluate its performance. Various sound examples demonstrate its expressive and musical potential. The source code, audio examples, tutorials, and software accompanying this work are available at https://cordutie.github.io/projects/qdts.html
