One-shot style transfer is a challenging task, since training on one utterance makes model extremely easy to over-fit to training data and causes low speaker similarity and lack of expressiveness. In this paper, we build on the recognition-synthesis framework and propose a one-shot voice conversion approach for style transfer based on speaker adaptation. First, a speaker normalization module is adopted to remove speaker-related information in bottleneck features extracted by ASR. Second, we adopt weight regularization in the adaptation process to prevent over-fitting caused by using only one utterance from target speaker as training data. Finally, to comprehensively decouple the speech factors, i.e., content, speaker, style, and transfer source style to the target, a prosody module is used to extract prosody representation. Experiments show that our approach is superior to the state-of-the-art one-shot VC systems in terms of style and speaker similarity; additionally, our approach also maintains good speech quality.
Single-step adversarial training (AT) has received wide attention as it proved to be both efficient and robust. However, a serious problem of catastrophic overfitting exists, i.e., the robust accuracy against projected gradient descent (PGD) attack suddenly drops to $0\%$ during the training. In this paper, we understand this problem from a novel perspective of optimization and firstly reveal the close link between the fast-growing gradient of each sample and overfitting, which can also be applied to understand the robust overfitting phenomenon in multi-step AT. To control the growth of the gradient during the training, we propose a new AT method, subspace adversarial training (Sub-AT), which constrains the AT in a carefully extracted subspace. It successfully resolves both two kinds of overfitting and hence significantly boosts the robustness. In subspace, we also allow single-step AT with larger steps and larger radius, which further improves the robustness performance. As a result, we achieve the state-of-the-art single-step AT performance: our pure single-step AT can reach over $\mathbf{51}\%$ robust accuracy against strong PGD-50 attack with radius $8/255$ on CIFAR-10, even surpassing the standard multi-step PGD-10 AT with huge computational advantages. The code is released$\footnote{\url{https://github.com/nblt/Sub-AT}}$.
The cross-speaker emotion transfer task in TTS particularly aims to synthesize speech for a target speaker with the emotion transferred from reference speech recorded by another (source) speaker. During the emotion transfer process, the identity information of the source speaker could also affect the synthesized results, resulting in the issue of speaker leakage. This paper proposes a new method with the aim to synthesize controllable emotional expressive speech and meanwhile maintain the target speaker's identity in the cross-speaker emotion TTS task. The proposed method is a Tacotron2-based framework with the emotion embedding as the conditioning variable to provide emotion information. Two emotion disentangling modules are contained in our method to 1) get speaker-independent and emotion-discriminative embedding, and 2) explicitly constrain the emotion and speaker identity of synthetic speech to be that as expected. Moreover, we present an intuitive method to control the emotional strength in the synthetic speech for the target speaker. Specifically, the learned emotion embedding is adjusted with a flexible scalar value, which allows controlling the emotion strength conveyed by the embedding. Extensive experiments have been conducted on a Mandarin disjoint corpus, and the results demonstrate that the proposed method is able to synthesize reasonable emotional speech for the target speaker. Compared to the state-of-the-art reference embedding learned methods, our method gets the best performance on the cross-speaker emotion transfer task, indicating that our method achieves the new state-of-the-art performance on learning the speaker-independent emotion embedding. Furthermore, the strength ranking test and pitch trajectories plots demonstrate that the proposed method can effectively control the emotion strength, leading to prosody-diverse synthetic speech.
Quantization has been proven to be a vital method for improving the inference efficiency of deep neural networks (DNNs). However, it is still challenging to strike a good balance between accuracy and efficiency while quantizing DNN weights or activation values from high-precision formats to their quantized counterparts. We propose a new method called elastic significant bit quantization (ESB) that controls the number of significant bits of quantized values to obtain better inference accuracy with fewer resources. We design a unified mathematical formula to constrain the quantized values of the ESB with a flexible number of significant bits. We also introduce a distribution difference aligner (DDA) to quantitatively align the distributions between the full-precision weight or activation values and quantized values. Consequently, ESB is suitable for various bell-shaped distributions of weights and activation of DNNs, thus maintaining a high inference accuracy. Benefitting from fewer significant bits of quantized values, ESB can reduce the multiplication complexity. We implement ESB as an accelerator and quantitatively evaluate its efficiency on FPGAs. Extensive experimental results illustrate that ESB quantization consistently outperforms state-of-the-art methods and achieves average accuracy improvements of 4.78%, 1.92%, and 3.56% over AlexNet, ResNet18, and MobileNetV2, respectively. Furthermore, ESB as an accelerator can achieve 10.95 GOPS peak performance of 1k LUTs without DSPs on the Xilinx ZCU102 FPGA platform. Compared with CPU, GPU, and state-of-the-art accelerators on FPGAs, the ESB accelerator can improve the energy efficiency by up to 65x, 11x, and 26x, respectively.
Current voice conversion (VC) methods can successfully convert timbre of the audio. As modeling source audio's prosody effectively is a challenging task, there are still limitations of transferring source style to the converted speech. This study proposes a source style transfer method based on recognition-synthesis framework. Previously in speech generation task, prosody can be modeled explicitly with prosodic features or implicitly with a latent prosody extractor. In this paper, taking advantages of both, we model the prosody in a hybrid manner, which effectively combines explicit and implicit methods in a proposed prosody module. Specifically, prosodic features are used to explicit model prosody, while VAE and reference encoder are used to implicitly model prosody, which take Mel spectrum and bottleneck feature as input respectively. Furthermore, adversarial training is introduced to remove speaker-related information from the VAE outputs, avoiding leaking source speaker information while transferring style. Finally, we use a modified self-attention based encoder to extract sentential context from bottleneck features, which also implicitly aggregates the prosodic aspects of source speech from the layered representations. Experiments show that our approach is superior to the baseline and a competitive system in terms of style transfer; meanwhile, the speech quality and speaker similarity are well maintained.
Recent years have witnessed significant advances in technologies and services in modern network applications, including smart grid management, wireless communication, cybersecurity as well as multi-agent autonomous systems. Considering the heterogeneous nature of networked entities, emerging network applications call for game-theoretic models and learning-based approaches in order to create distributed network intelligence that responds to uncertainties and disruptions in a dynamic or an adversarial environment. This paper articulates the confluence of networks, games and learning, which establishes a theoretical underpinning for understanding multi-agent decision-making over networks. We provide an selective overview of game-theoretic learning algorithms within the framework of stochastic approximation theory, and associated applications in some representative contexts of modern network systems, such as the next generation wireless communication networks, the smart grid and distributed machine learning. In addition to existing research works on game-theoretic learning over networks, we highlight several new angles and research endeavors on learning in games that are related to recent developments in artificial intelligence. Some of the new angles extrapolate from our own research interests. The overall objective of the paper is to provide the reader a clear picture of the strengths and challenges of adopting game-theoretic learning methods within the context of network systems, and further to identify fruitful future research directions on both theoretical and applied studies.
The acceleration of CNNs has gained increasing atten-tion since their success in computer vision. With the heterogeneous functional layers that cannot be pro-cessed by the accelerators proposed for convolution layers only, modern end-to-end CNN acceleration so-lutions either transform the diverse computation into matrix/vector arithmetic, which loses data reuse op-portunities in convolution, or introduce dedicated functional unit to each kind of layer, which results in underutilization and high update expense. To enhance the whole-life cost efficiency, we need an acceleration solution that is efficient in processing CNN layers and has the generality to apply to all kinds of existing and emerging layers. To this end, we pro-pose GCONV Chain, a method to convert the entire CNN computation into a chain of standard general convolutions (GCONV) that can be efficiently pro-cessed by the existing CNN accelerators. This paper comprehensively analyzes the GCONV Chain model and proposes a full-stack implementation to support GCONV Chain. On one hand, the results on seven var-ious CNNs demonstrate that GCONV Chain improves the performance and energy efficiency of existing CNN accelerators by an average of 3.4x and 3.2x re-spectively. On the other hand, we show that GCONV Chain provides low whole-life costs for CNN accelera-tion, including both developer efforts and total cost of ownership for the users.
There is a growing privacy concern due to the popularity of social media and surveillance systems, along with advances in face recognition software. However, established image obfuscation techniques are either vulnerable to re-identification attacks by human or deep learning models, insufficient in preserving image fidelity, or too computationally intensive to be practical. To tackle these issues, we present DeepBlur, a simple yet effective method for image obfuscation by blurring in the latent space of an unconditionally pre-trained generative model that is able to synthesize photo-realistic facial images. We compare it with existing methods by efficiency and image quality, and evaluate against both state-of-the-art deep learning models and industrial products (e.g., Face++, Microsoft face service). Experiments show that our method produces high quality outputs and is the strongest defense for most test cases.