Adaptable GAN Encoders for Image Reconstruction via Multi-type Latent Vectors with Two-scale Attentions

Although current deep generative adversarial networks (GANs) could synthesize high-quality (HQ) images, discovering novel GAN encoders for image reconstruction is still favorable. When embedding images to latent space, existing GAN encoders work well for aligned images (such as the human face), but they do not adapt to more generalized GANs. To our knowledge, current state-of-the-art GAN encoders do not have a proper encoder to reconstruct high-fidelity images from most misaligned HQ synthesized images on different GANs. Their performances are limited, especially on non-aligned and real images. We propose a novel method (named MTV-TSA) to handle such problems. Creating multi-type latent vectors (MTV) from latent space and two-scale attentions (TSA) from images allows designing a set of encoders that can be adaptable to a variety of pre-trained GANs. We generalize two sets of loss functions to optimize the encoders. The designed encoders could make GANs reconstruct higher fidelity images from most synthesized HQ images. In addition, the proposed method can reconstruct real images well and process them based on learned attribute directions. The designed encoders have unified convolutional blocks and could match well in current GAN architectures (such as PGGAN, StyleGANs, and BigGAN) by fine-tuning the corresponding normalization layers and the last block. Such well-designed encoders can also be trained to converge more quickly.

Intermittent Speech Recovery

A large number of Internet of Things (IoT) devices today are powered by batteries, which are often expensive to maintain and may cause serious environmental pollution. To avoid these problems, researchers have begun to consider the use of energy systems based on energy-harvesting units for such devices. However, the power harvested from an ambient source is fundamentally small and unstable, resulting in frequent power failures during the operation of IoT applications involving, for example, intermittent speech signals and the streaming of videos. This paper presents a deep-learning-based speech recovery system that reconstructs intermittent speech signals from self-powered IoT devices. Our intermittent speech recovery system (ISR) consists of three stages: interpolation, recovery, and combination. The experimental results show that our recovery system increases speech quality by up to 707.1%, while increasing speech intelligibility by up to 92.1%. Most importantly, our ISR system also enhances the WER scores by up to 65.6%. To the best of our knowledge, this study is one of the first to reconstruct intermittent speech signals from self-powered-sensing IoT devices. These promising results suggest that even though self powered microphone devices function with weak energy sources, our ISR system can still maintain the performance of most speech-signal-based applications.

MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement

The discrepancy between the cost function used for training a speech enhancement model and human auditory perception usually makes the quality of enhanced speech unsatisfactory. Objective evaluation metrics which consider human perception can hence serve as a bridge to reduce the gap. Our previously proposed MetricGAN was designed to optimize objective metrics by connecting the metric with a discriminator. Because only the scores of the target evaluation functions are needed during training, the metrics can even be non-differentiable. In this study, we propose a MetricGAN+ in which three training techniques incorporating domain-knowledge of speech processing are proposed. With these techniques, experimental results on the VoiceBank-DEMAND dataset show that MetricGAN+ can increase PESQ score by 0.3 compared to the previous MetricGAN and achieve state-of-the-art results (PESQ score = 3.15).

Attention-based multi-task learning for speech-enhancement and speaker-identification in multi-speaker dialogue scenario

Multi-task learning (MTL) and the attention technique have been proven to effectively extract robust acoustic features for various speech-related applications in noisy environments. In this study, we integrated MTL and the attention-weighting mechanism and propose an attention-based MTL (ATM0 approach to realize a multi-model learning structure and to promote the speech enhancement (SE) and speaker identification (SI) systems simultaneously. There are three subsystems in the proposed ATM: SE, SI, and attention-Net (AttNet). In the proposed system, a long-short-term memory (LSTM) is used to perform SE, while a deep neural network (DNN) model is applied to construct SI and AttNet in ATM. The overall ATM system first extracts the representative features and then enhances the speech spectra in LSTM-SE and classifies speaker identity in DNN-SI. We conducted our experiment on Taiwan Mandarin hearing in noise test database. The evaluation results indicate that the proposed ATM system not only increases the quality and intelligibility of noisy speech input but also improves the accuracy of the SI system when compared to the conventional MTL approaches.

Shaping Deep Feature Space towards Gaussian Mixture for Visual Classification

The softmax cross-entropy loss function has been widely used to train deep models for various tasks. In this work, we propose a Gaussian mixture (GM) loss function for deep neural networks for visual classification. Unlike the softmax cross-entropy loss, our method explicitly shapes the deep feature space towards a Gaussian Mixture distribution. With a classification margin and a likelihood regularization, the GM loss facilitates both high classification performance and accurate modeling of the feature distribution. The GM loss can be readily used to distinguish abnormal inputs, such as the adversarial examples, based on the discrepancy between feature distributions of the inputs and the training set. Furthermore, theoretical analysis shows that a symmetric feature space can be achieved by using the GM loss, which enables the models to perform robustly against adversarial attacks. The proposed model can be implemented easily and efficiently without using extra trainable parameters. Extensive evaluations demonstrate that the proposed method performs favorably not only on image classification but also on robust detection of adversarial examples generated by strong attacks under different threat models.

Improving Perceptual Quality by Phone-Fortified Perceptual Loss for Speech Enhancement

Speech enhancement (SE) aims to improve speech quality and intelligibility, which are both related to a smooth transition in speech segments that may carry linguistic information, e.g. phones and syllables. In this study, we took phonetic characteristics into account in the SE training process. Hence, we designed a phone-fortified perceptual (PFP) loss, and the training of our SE model was guided by PFP loss. In PFP loss, phonetic characteristics are extracted by wav2vec, an unsupervised learning model based on the contrastive predictive coding (CPC) criterion. Different from previous deep-feature-based approaches, the proposed approach explicitly uses the phonetic information in the deep feature extraction process to guide the SE model training. To test the proposed approach, we first confirmed that the wav2vec representations carried clear phonetic information using a t-distributed stochastic neighbor embedding (t-SNE) analysis. Next, we observed that the proposed PFP loss was more strongly correlated with the perceptual evaluation metrics than point-wise and signal-level losses, thus achieving higher scores for standardized quality and intelligibility evaluation metrics in the Voice Bank-DEMAND dataset.

Multi-Scale Networks for 3D Human Pose Estimation with Inference Stage Optimization

Estimating 3D human poses from a monocular video is still a challenging task. Many existing methods' performance drops when the target person is occluded by other objects, or the motion is too fast/slow relative to the scale and speed of the training data. Moreover, many of these methods are not designed or trained under severe occlusion explicitly, making their performance on handling occlusion compromised. Addressing these problems, we introduce a spatio-temporal network for robust 3D human pose estimation. As humans in videos may appear in different scales and have various motion speeds, we apply multi-scale spatial features for 2D joints or keypoints prediction in each individual frame, and multi-stride temporal convolutional networks (TCNs) to estimate 3D joints or keypoints. Furthermore, we design a spatio-temporal discriminator based on body structures as well as limb motions to assess whether the predicted pose forms a valid pose and a valid movement. During training, we explicitly mask out some keypoints to simulate various occlusion cases, from minor to severe occlusion, so that our network can learn better and becomes robust to various degrees of occlusion. As there are limited 3D ground-truth data, we further utilize 2D video data to inject a semi-supervised learning capability to our network. Moreover, we observe that there is a discrepancy between 3D pose prediction and 2D pose estimation due to different pose variations between video and image training datasets. We, therefore propose a confidence-based inference stage optimization to adaptively enforce 3D pose projection to match 2D pose estimation to further improve final pose prediction accuracy. Experiments on public datasets validate the effectiveness of our method, and our ablation studies show the strengths of our network's individual submodules.

Boosting Objective Scores of Speech Enhancement Model through MetricGAN Post-Processing

The Transformer architecture has shown its superior ability than recurrent neural networks on many different natural language processing applications. Therefore, this study applies a modified Transformer on the speech enhancement task. Specifically, the positional encoding may not be necessary and hence is replaced by convolutional layers. To further improve PESQ scores of enhanced speech, the L_1 pre-trained Transformer is fine-tuned by MetricGAN framework. The proposed MetricGAN can be treated as a general post-processing module to further boost interested objective scores. The experiments are conducted using the data sets provided by the organizer of the Deep Noise Suppression (DNS) challenge. Experimental results demonstrate that the proposed system outperforms the challenge baseline in both subjective and objective evaluation with a large margin.

Increasing Compactness Of Deep Learning Based Speech Enhancement Models With Parameter Pruning And Quantization Techniques

Most recent studies on deep learning based speech enhancement (SE) focused on improving denoising performance. However, successful SE applications require striking a desirable balance between denoising performance and computational cost in real scenarios. In this study, we propose a novel parameter pruning (PP) technique, which removes redundant channels in a neural network. In addition, a parameter quantization (PQ) technique was applied to reduce the size of a neural network by representing weights with fewer cluster centroids. Because the techniques are derived based on different concepts, the PP and PQ can be integrated to provide even more compact SE models. The experimental results show that the PP and PQ techniques produce a compacted SE model with a size of only 10.03% compared to that of the original model, resulting in minor performance losses of 1.43% (from 0.70 to 0.69) for STOI and 3.24% (from 1.85 to 1.79) for PESQ. The promising results suggest that the PP and PQ techniques can be used in a SE system in devices with limited storage and computation resources.