Related papers: Improving GANs for Speech Enhancement

We present a new stage-wise learning paradigm for training generative adversarial networks (GANs). The goal of our work is to progressively strengthen the discriminator and thus, the generators, with each subsequent stage without changing…

Deep learning has become a de facto method of choice for speech enhancement tasks with significant improvements in speech quality. However, real-time processing with reduced size and computations for low-power edge devices drastically…

One of the most significant challenges in statistical signal processing and machine learning is how to obtain a generative model that can produce samples of large-scale data distribution, such as images and speeches. Generative Adversarial…

Domain adaptation plays an important role for speech recognition models, in particular, for domains that have low resources. We propose a novel generative model based on cyclic-consistent generative adversarial network (CycleGAN) for…

It is still a challenging task to learn a neural text generation model under the framework of generative adversarial networks (GANs) since the entire training process is not differentiable. The existing training strategies either suffer…

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…

Generative Adversarial Networks (GANs) enjoy great success at image generation, but have proven difficult to train in the domain of natural language. Challenges with gradient estimation, optimization instability, and mode collapse have lead…

The research in Environmental Sound Classification (ESC) has been progressively growing with the emergence of deep learning algorithms. However, data scarcity poses a major hurdle for any huge advance in this domain. Data augmentation…

Generative Adversarial Networks (GANs) have seen steep ascension to the peak of ML research zeitgeist in recent years. Mostly catalyzed by its success in the domain of image generation, the technique has seen wide range of adoption in a…

We propose to improve unconditional Generative Adversarial Networks (GAN) by training the self-supervised learning with the adversarial process. In particular, we apply self-supervised learning via the geometric transformation on input…

We present a continual learning approach for generative adversarial networks (GANs), by designing and leveraging parameter-efficient feature map transformations. Our approach is based on learning a set of global and task-specific…

The human brain contextually exploits heterogeneous sensory information to efficiently perform cognitive tasks including vision and hearing. For example, during the cocktail party situation, the human auditory cortex contextually integrates…

Generative adversarial networks (GANs) are powerful generative models, but usually suffer from instability and generalization problem which may lead to poor generations. Most existing works focus on stabilizing the training of the…

Although Generative Adversarial Networks (GANs) have shown remarkable success in various tasks, they still face challenges in generating high quality images. In this paper, we propose Stacked Generative Adversarial Networks (StackGAN)…

Our voice encodes a uniquely identifiable pattern which can be used to infer private attributes, such as gender or identity, that an individual might wish not to reveal when using a speech recognition service. To prevent attribute inference…

Generative adversarial network (GAN) has achieved impressive success on cross-domain generation, but it faces difficulty in cross-modal generation due to the lack of a common distribution between heterogeneous data. Most existing methods of…

The advance of Generative Adversarial Networks (GANs) enables realistic face image synthesis. However, synthesizing face images that preserve facial identity as well as have high diversity within each identity remains challenging. To…

Speech enhancement concerns the processes required to remove unwanted background sounds from the target speech to improve its quality and intelligibility. In this paper, a novel approach for single-channel speech enhancement is presented,…

Whistle contour extraction aims to derive animal whistles from time-frequency spectrograms as polylines. For toothed whales, whistle extraction results can serve as the basis for analyzing animal abundance, species identity, and social…

Traditional generative adversarial networks (GAN) and many of its variants are trained by minimizing the KL or JS-divergence loss that measures how close the generated data distribution is from the true data distribution. A recent advance…