相关论文: GAN-based Generation and Automatic Selection of Ex…

Significant advances in deep learning have led to more widely used and precise neural network-based generative models such as Generative Adversarial Networks (GANs). We introduce a post-hoc correction to deep generative models to further…

The choice of parameters, and the design of the network architecture are important factors affecting the performance of deep neural networks. However, there has not been much work on developing an established and systematic way of building…

Click-Through Rate prediction is an important task in recommender systems, which aims to estimate the probability of a user to click on a given item. Recently, many deep models have been proposed to learn low-order and high-order feature…

Insufficient recordings and the scarcity of anomalies present significant challenges in developing and validating robust anomaly detection systems for machine sounds. To address these limitations, we propose a novel approach for generating…

Due to the superior modeling ability of deep neural network (DNN), it is widely used in voice activity detection (VAD). However, the performance may degrade if no sufficient data especially for practical data could be used for training,…

Speech enhancement involves the distinction of a target speech signal from an intrusive background. Although generative approaches using Variational Autoencoders or Generative Adversarial Networks (GANs) have increasingly been used in…

The Generative Adversarial Network (GAN) has achieved great success in generating realistic (real-valued) synthetic data. However, convergence issues and difficulties dealing with discrete data hinder the applicability of GAN to text. We…

Learning disentangled representation of data without supervision is an important step towards improving the interpretability of generative models. Despite recent advances in disentangled representation learning, existing approaches often…

We develop a novel method for training of GANs for unsupervised and class conditional generation of images, called Linear Discriminant GAN (LD-GAN). The discriminator of an LD-GAN is trained to maximize the linear separability between…

Existing dominant methods for audio generation include Generative Adversarial Networks (GANs) and diffusion-based methods like Flow Matching. GANs suffer from slow convergence during training, while diffusion methods require multi-step…

Automatic generation of paraphrases from a given sentence is an important yet challenging task in natural language processing (NLP), and plays a key role in a number of applications such as question answering, search, and dialogue. In this…

Melody generation from lyrics has been a challenging research issue in the field of artificial intelligence and music, which enables to learn and discover latent relationship between interesting lyrics and accompanying melody.…

We studied the ability of deep neural networks (DNNs) to restore missing audio content based on its context, a process usually referred to as audio inpainting. We focused on gaps in the range of tens of milliseconds. The proposed DNN…

Over the past few decades, extensive research has been devoted to the design of artificial reverberation algorithms aimed at emulating the room acoustics of physical environments. Despite significant advancements, automatic parameter tuning…

Research and education in machine learning needs diverse, representative, and open datasets that contain sufficient samples to handle the necessary training, validation, and testing tasks. Currently, the Recommender Systems area includes a…

Accurately detecting voiced intervals in speech signals is a critical step in pitch tracking and has numerous applications. While conventional signal processing methods and deep learning algorithms have been proposed for this task, their…

Speechreading is the task of inferring phonetic information from visually observed articulatory facial movements, and is a notoriously difficult task for humans to perform. In this paper we present an end-to-end model based on a…

Deep neural networks (DNNs) achieve remarkable predictive performance but remain difficult to interpret, largely due to overparameterization that obscures the minimal structure required for interpretation. Here we introduce DeepIn, a…

Generative Adversarial Networks (GANs) have recently achieved unprecedented success in photo-realistic image synthesis from low-dimensional random noise. The ability to synthesize high-quality content at a large scale brings potential risks…

Separating two sources from an audio mixture is an important task with many applications. It is a challenging problem since only one signal channel is available for analysis. In this paper, we propose a novel framework for singing voice…