arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2301.02886cs.SDcs.LGeess.AS
收藏

感知-神经-物理声音匹配

Perceptual-Neural-Physical Sound Matching

Nantes Université(南特大学);École Centrale Nantes(南特中央理工学院);CNRS(法国国家科学研究中心);LS2N(南特数字科学实验室)

Han Han, Vincent Lostanlen, Mathieu Lagrange

摘要:

声音匹配算法试图通过参数音频合成来近似目标波形。深度神经网络在匹配持续谐波音调方面取得了令人鼓舞的结果。然而,当目标是非平稳和非谐波时,例如,打击乐我们把这个问题归结为损失函数的不足。一方面,在参数域中的均方误差,被称为“P损失”,是简单和快速的,但不能适应每个参数的不同感知意义。另一方面,均方误差在频谱时域,被称为“频谱损失”,是感知动机,并在可微数字信号处理(DDSP)。然而,频谱损失是音调间隔的差的预测器,并且其梯度可能在计算上是昂贵的;因此收敛缓慢。针对这个难题,我们提出了感知神经物理损失(PNP)。PNP是频谱损失的最佳二次近似,同时在训练期间与P损失一样快。我们用物理模型合成作为解码器,联合时频散射变换(JTFS)作为谱表示来实例化PNP。与其他损失函数相比,我们证明了它在匹配合成鼓声方面的潜力。

英文摘要:

Sound matching algorithms seek to approximate a target waveform by parametric audio synthesis. Deep neural networks have achieved promising results in matching sustained harmonic tones. However, the task is more challenging when targets are nonstationary and inharmonic, e.g., percussion. We attribute this problem to the inadequacy of loss function. On one hand, mean square error in the parametric domain, known as "P-loss", is simple and fast but fails to accommodate the differing perceptual significance of each parameter. On the other hand, mean square error in the spectrotemporal domain, known as "spectral loss", is perceptually motivated and serves in differentiable digital signal processing (DDSP). Yet, spectral loss is a poor predictor of pitch intervals and its gradient may be computationally expensive; hence a slow convergence. Against this conundrum, we present Perceptual-Neural-Physical loss (PNP). PNP is the optimal quadratic approximation of spectral loss while being as fast as P-loss during training. We instantiate PNP with physical modeling synthesis as decoder and joint time-frequency scattering transform (JTFS) as spectral representation. We demonstrate its potential on matching synthetic drum sounds in comparison with other loss functions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑