Related papers: A Style Transfer Approach to Source Separation

Recently, Transformer has achieved the state-of-the-art performance on many machine translation tasks. However, without syntax knowledge explicitly considered in the encoder, incorrect context information that violates the syntax structure…

How can we learn, transfer and extract handwriting styles using deep neural networks? This paper explores these questions using a deep conditioned autoencoder on the IRON-OFF handwriting data-set. We perform three experiments that…

Text-style transfer aims to convert text given in one domain into another by paraphrasing the sentence or substituting the keywords without altering the content. By necessity, state-of-the-art methods have evolved to accommodate nonparallel…

Many methods have been proposed to solve the domain adaptation problem recently. However, the success of them implicitly funds on the assumption that the information of domains are fully transferrable. If the assumption is not satisfied,…

Deep learning models that are trained on histopathological images obtained from a single lab and/or scanner give poor inference performance on images obtained from another scanner/lab with a different staining protocol. In recent years,…

We address the problem of style transfer between two photos and propose a new way to preserve photorealism. Using the single pair of photos available as input, we train a pair of deep convolution networks (convnets), each of which transfers…

Significant challenges exist in efficient data analysis of most advanced experimental and observational techniques because the collected signals often include unwanted contributions--such as background and signal distortions--that can…

In this paper, we present a novel training method for speaker change detection models. Speaker change detection is often viewed as a binary sequence labelling problem. The main challenges with this approach are the vagueness of annotated…

Speech separation seeks to isolate individual speech signals from a multi-talk speech mixture. Despite much progress, a system well-trained on synthetic data often experiences performance degradation on out-of-domain data, such as…

Designing fonts requires a great deal of time and effort. It requires professional skills, such as sketching, vectorizing, and image editing. Additionally, each letter has to be designed individually. In this paper, we will introduce a…

A new learning algorithm for speech separation networks is designed to explicitly reduce residual noise and artifacts in the separated signal in an unsupervised manner. Generative adversarial networks are known to be effective in…

In this paper, we propose the problem of domain transfer structured output learn- ing and the first solution to solve it. The problem is defined on two different data domains sharing the same input and output spaces, named as source domain…

A crucial challenge in reinforcement learning is to reduce the number of interactions with the environment that an agent requires to master a given task. Transfer learning proposes to address this issue by re-using knowledge from previously…

This paper introduces a deep-learning approach to photographic style transfer that handles a large variety of image content while faithfully transferring the reference style. Our approach builds upon the recent work on painterly transfer…

Programming languages are emerging as a challenging and interesting domain for machine learning. A core task, which has received significant attention in recent years, is building generative models of source code. However, to our knowledge,…

Audio source separation is fundamental for machines to understand complex acoustic environments and underpins numerous audio applications. Current supervised deep learning approaches, while powerful, are limited by the need for extensive,…

Direct speech-to-speech translation (S2ST) with discrete self-supervised representations has achieved remarkable accuracy, but is unable to preserve the speaker timbre of the source speech. Meanwhile, the scarcity of high-quality…

Neural networks are susceptible to adversarial perturbations that are transferable across different models. In this paper, we introduce a novel model alignment technique aimed at improving a given source model's ability in generating…

Even though a linguistics-free sequence to sequence model in neural machine translation (NMT) has certain capability of implicitly learning syntactic information of source sentences, this paper shows that source syntax can be explicitly…

Supervised learning for single-channel speech enhancement requires carefully labeled training examples where the noisy mixture is input into the network and the network is trained to produce an output close to the ideal target. To relax the…