Can we develop a model that can synthesize realistic speech directly from a
latent space, without explicit conditioning? Despite several efforts over the
last decade, previous adversarial and diffusion-based approaches still struggle
to achieve this, even on small-vocabulary datasets. To address this, we propose
AudioStyleGAN (ASGAN) -- a generative adversarial network for unconditional
speech synthesis tailored to learn a disentangled latent space. Building upon
the StyleGAN family of image synthesis models, ASGAN maps sampled noise to a
disentangled latent vector which is then mapped to a sequence of audio features
so that signal aliasing is suppressed at every layer. To successfully train
ASGAN, we introduce a number of new techniques, including a modification to
adaptive discriminator augmentation which probabilistically skips discriminator
updates. We apply it on the small-vocabulary Google Speech Commands digits
dataset, where it achieves state-of-the-art results in unconditional speech
synthesis. It is also substantially faster than existing top-performing
diffusion models. We confirm that ASGAN's latent space is disentangled: we
demonstrate how simple linear operations in the space can be used to perform
several tasks unseen during training. Specifically, we perform evaluations in
voice conversion, speech enhancement, speaker verification, and keyword
classification. Our work indicates that GANs are still highly competitive in
the unconditional speech synthesis landscape, and that disentangled latent
spaces can be used to aid generalization to unseen tasks. Code, models,
samples: this https URL

提出了一种基于生成对抗网络的音频合成模型 (ASGAN)，它在一个解耦的潜空间中对音频序列进行建模，并且通过引入自适应鉴别器增强技术的修改，它在无条件语音合成领域达到了最先进的水平。

无条件语音合成中 GAN 的解缠

Disentanglement in a GAN for Unconditional Speech Synthesis

We introduce MotionCLIP, a 3D human motion auto-encoder featuring a latent
embedding that is disentangled, well behaved, and supports highly semantic
textual descriptions. MotionCLIP gains its unique power by aligning its latent
space with that of the Contrastive Language-Image Pre-training (CLIP) model.
Aligning the human motion manifold to CLIP space implicitly infuses the
extremely rich semantic knowledge of CLIP into the manifold. In particular, it
helps continuity by placing semantically similar motions close to one another,
and disentanglement, which is inherited from the CLIP-space structure.
MotionCLIP comprises a transformer-based motion auto-encoder, trained to
reconstruct motion while being aligned to its text label's position in
CLIP-space. We further leverage CLIP's unique visual understanding and inject
an even stronger signal through aligning motion to rendered frames in a
self-supervised manner. We show that although CLIP has never seen the motion
domain, MotionCLIP offers unprecedented text-to-motion abilities, allowing
out-of-domain actions, disentangled editing, and abstract language
specification. For example, the text prompt "couch" is decoded into a sitting
down motion, due to lingual similarity, and the prompt "Spiderman" results in a
web-swinging-like solution that is far from seen during training. In addition,
we show how the introduced latent space can be leveraged for motion
interpolation, editing and recognition.

MotionCLIP 是一种 3D 人体运动自编码器，在 latent space 中对接 CLIP 模型，以获得无与伦比的文本到运动的能力，实现了跨域动作，编辑和抽象语言规范等功能。

MotionCLIP: 将人体动作生成暴露到 CLIP 空间

MotionCLIP: Exposing Human Motion Generation to CLIP Space

Recent work has made significant progress on using implicit functions, as a
continuous representation for 3D rigid object shape reconstruction. However,
much less effort has been devoted to modeling general articulated objects.
Compared to rigid objects, articulated objects have higher degrees of freedom,
which makes it hard to generalize to unseen shapes. To deal with the large
shape variance, we introduce Articulated Signed Distance Functions (A-SDF) to
represent articulated shapes with a disentangled latent space, where we have
separate codes for encoding shape and articulation. We assume no prior
knowledge on part geometry, articulation status, joint type, joint axis, and
joint location. With this disentangled continuous representation, we
demonstrate that we can control the articulation input and animate unseen
instances with unseen joint angles. Furthermore, we propose a Test-Time
Adaptation inference algorithm to adjust our model during inference. We
demonstrate our model generalize well to out-of-distribution and unseen data,
e.g., partial point clouds and real-world depth images.

该研究论文提出了一种使用关节的带符号距离函数来表示动态物体的连续重建方法，并实现了对动态物体建模的控制和动画。

A-SDF: 学习解耦有符号距离函数以表示关节形状

A-SDF: Learning Disentangled Signed Distance Functions for Articulated  Shape Representation

In recent years, applying Deep Learning (DL) techniques emerged as a common
practice in the communication system, demonstrating promising results. The
present paper proposes a new Convolutional Neural Network (CNN) based
Variational Autoencoder (VAE) communication system. The VAE (continuous latent
space) based communication systems confer unprecedented improvement in the
system performance compared to AE (distributed latent space) and other
traditional methods. We have introduced an adjustable hyperparameter beta in
the proposed VAE, which is also known as beta-VAE, resulting in extremely
disentangled latent space representation. Furthermore, a higher-dimensional
representation of latent space is employed, such as 4n dimension instead of 2n,
reducing the Block Error Rate (BLER). The proposed system can operate under
Additive Wide Gaussian Noise (AWGN) and Rayleigh fading channels. The CNN based
VAE architecture performs the encoding and modulation at the transmitter,
whereas decoding and demodulation at the receiver. Finally, to prove that a
continuous latent space-based system designated VAE performs better than the
other, various simulation results supporting the same has been conferred under
normal and noisy conditions.

本文提出了一种基于 CNN 的 VAE 通信系统，使用可调节超参数 beta 的 VAE 架构，在传统方法中表现卓越，具有极度脱耦的潜在空间表现，使得基于连续潜在空间的 VAE 系统比其他系统表现更佳。