论文标题
自动编码神经网络作为音乐音频合成器
Autoencoding Neural Networks as Musical Audio Synthesizers
论文作者
论文摘要
提出了一种使用自动编码神经网络进行音乐音频合成的方法。对自动编码器进行了训练，可以压缩和重建短时傅立叶变换帧。自动编码器通过激活其最小的隐藏层产生频谱图，并使用实时相位梯度堆积分来计算相位响应。进行反向短时傅立叶变换会产生音频信号。与当前最新的音频机器学习算法相比，我们的算法很重。我们概述了设计过程，制作指标，并详细介绍了模型的开源Python实现。
A method for musical audio synthesis using autoencoding neural networks is proposed. The autoencoder is trained to compress and reconstruct magnitude short-time Fourier transform frames. The autoencoder produces a spectrogram by activating its smallest hidden layer, and a phase response is calculated using real-time phase gradient heap integration. Taking an inverse short-time Fourier transform produces the audio signal. Our algorithm is light-weight when compared to current state-of-the-art audio-producing machine learning algorithms. We outline our design process, produce metrics, and detail an open-source Python implementation of our model.
