Over the past few years, speech enhancement methods based on deep learning
have greatly surpassed traditional methods based on spectral subtraction and
spectral estimation. Many of these new techniques operate directly in the the
short-time Fourier transform (STFT) domain, resulting in a high computational
complexity. In this work, we propose PercepNet, an efficient approach that
relies on human perception of speech by focusing on the spectral envelope and
on the periodicity of the speech. We demonstrate high-quality, real-time
enhancement of fullband (48 kHz) speech with less than 5% of a CPU core.

本文提出了一种称之为 PercepNet 的用于语音增强的深度学习方法，该方法仅需要短时间的傅里叶变换，通过聚焦于语音的谱包络和周期性，可以实现高质量、实时的全频带语音增强，仅需要不到 5% 的 CPU 核心。

一种感知动机的方法用于低复杂度、实时完整语音的增强

A Perceptually-Motivated Approach for Low-Complexity, Real-Time  Enhancement of Fullband Speech

Musical performance combines a wide range of pitches, nuances, and expressive
techniques. Audio-based classification of musical instruments thus requires to
build signal representations that are invariant to such transformations. This
article investigates the construction of learned convolutional architectures
for instrument recognition, given a limited amount of annotated training data.
In this context, we benchmark three different weight sharing strategies for
deep convolutional networks in the time-frequency domain: temporal kernels;
time-frequency kernels; and a linear combination of time-frequency kernels
which are one octave apart, akin to a Shepard pitch spiral. We provide an
acoustical interpretation of these strategies within the source-filter
framework of quasi-harmonic sounds with a fixed spectral envelope, which are
archetypal of musical notes. The best classification accuracy is obtained by
hybridizing all three convolutional layers into a single deep learning
architecture.

本研究调查了构建学习卷积网络用于乐器识别的问题，并对三种不同的权重共享策略进行了性能测试，结果表明混合三种卷积层在单个深度学习体系结构中的效果最佳。