Related papers: Boosting Star-GANs for Voice Conversion with Contr…

This paper shows that StarGAN-VC, a spectral envelope transformation method for non-parallel many-to-many voice conversion (VC), is capable of emotional VC (EVC). Although StarGAN-VC has been shown to enable speaker identity conversion, its…

Recent advancement in Generative Adversarial Networks in speech synthesis domain[3],[2] have shown, that it's possible to train GANs [8] in a reliable manner for high quality coherent waveform generation from mel-spectograms. We propose…

A text-to-speech (TTS) model trained to reconstruct speech given text tends towards predictions that are close to the average characteristics of a dataset, failing to model the variations that make human speech sound natural. This problem…

Besides the well-known classification task, these days neural networks are frequently being applied to generate or transform data, such as images and audio signals. In such tasks, the conventional loss functions like the mean squared error…

We propose AudioStyleGAN (ASGAN), a new generative adversarial network (GAN) for unconditional speech synthesis. As in the StyleGAN family of image synthesis models, ASGAN maps sampled noise to a disentangled latent vector which is then…

Conditional generation is a subclass of generative problems where the output of the generation is conditioned by the attribute information. In this paper, we present a stochastic contrastive conditional generative adversarial network…

Recommendation techniques are important approaches for alleviating information overload. Being often trained on implicit user feedback, many recommenders suffer from the sparsity challenge due to the lack of explicitly negative samples. The…

Current speech enhancement techniques operate on the spectral domain and/or exploit some higher-level feature. The majority of them tackle a limited number of noise conditions and rely on first-order statistics. To circumvent these issues,…

In classification tasks, the classification accuracy diminishes when the data is gathered in different domains. To address this problem, in this paper, we investigate several adversarial models for domain adaptation (DA) and their effect on…

Perturbative GAN, which replaces convolution layers of existing convolutional GANs (DCGAN, WGAN-GP, BIGGAN, etc.) with perturbation layers that adds a fixed noise mask, is proposed. Compared with the convolu-tional GANs, the number of…

This paper proposes voicing-aware conditional discriminators for Parallel WaveGAN-based waveform synthesis systems. In this framework, we adopt a projection-based conditioning method that can significantly improve the discriminator's…

Class-conditional image generation using generative adversarial networks (GANs) has been investigated through various techniques; however, it continues to face challenges such as mode collapse, training instability, and low-quality output…

In this study, we propose a novel noise adaptive speech enhancement (SE) system, which employs a domain adversarial training (DAT) approach to tackle the issue of a noise type mismatch between the training and testing conditions. Such a…

We propose SelfVC, a training strategy to iteratively improve a voice conversion model with self-synthesized examples. Previous efforts on voice conversion focus on factorizing speech into explicitly disentangled representations that…

Speech enhancement at extremely low signal-to-noise ratio (SNR) condition is a very challenging problem and rarely investigated in previous works. This paper proposes a robust speech enhancement approach (UNetGAN) based on U-Net and…

We propose a novel training algorithm for a multi-speaker neural text-to-speech (TTS) model based on multi-task adversarial training. A conventional generative adversarial network (GAN)-based training algorithm significantly improves the…

The training of Generative Adversarial Networks is a difficult task mainly due to the nature of the networks. One such issue is when the generator and discriminator start oscillating, rather than converging to a fixed point. Another case…

Despite success on a wide range of problems related to vision, generative adversarial networks (GANs) often suffer from inferior performance due to unstable training, especially for text generation. To solve this issue, we propose a new…

Speech enhancement aims to obtain speech signals with high intelligibility and quality from noisy speech. Recent work has demonstrated the excellent performance of time-domain deep learning methods, such as Conv-TasNet. However, these…

This study delves into the application of Generative Adversarial Networks (GANs) within the context of imbalanced datasets. Our primary aim is to enhance the performance and stability of GANs in such datasets. In pursuit of this objective,…