Related papers: Stable Style Transformer: Delete and Generate Appr…

While unbiased machine learning models are essential for many applications, bias is a human-defined concept that can vary across tasks. Given only input-label pairs, algorithms may lack sufficient information to distinguish stable (causal)…

In this paper, we present a Diffusion GAN based approach (Prosodic Diff-TTS) to generate the corresponding high-fidelity speech based on the style description and content text as an input to generate speech samples within only 4 denoising…

Universal Neural Style Transfer (NST) methods are capable of performing style transfer of arbitrary styles in a style-agnostic manner via feature transforms in (almost) real-time. Even though their unimodal parametric style modeling…

Text style transfer is an exciting task within the field of natural language generation that is often plagued by the need for high-quality paired datasets. Furthermore, training a model for multi-attribute text style transfer requires…

Existing neural style transfer researches have studied to match statistical information between the deep features of content and style images, which were extracted by a pre-trained VGG, and achieved significant improvement in synthesizing…

In this paper we propose a new generative model of text, Step-unrolled Denoising Autoencoder (SUNDAE), that does not rely on autoregressive models. Similarly to denoising diffusion techniques, SUNDAE is repeatedly applied on a sequence of…

Text simplification (TS) aims to reduce the lexical and structural complexity of a text, while still retaining the semantic meaning. Current automatic TS techniques are limited to either lexical-level applications or manually defining a…

The rapid development of such natural language processing tasks as style transfer, paraphrase, and machine translation often calls for the use of semantic similarity metrics. In recent years a lot of methods to measure the semantic…

Large Language Models (LLMs) are emerging as dominant forces for textual style transfer. However, for arbitrary style transfer, LLMs face two key challenges: (1) considerable reliance on manually-constructed prompts and (2) rigid stylistic…

In this paper, we focus on a new practical task, document-scale text content manipulation, which is the opposite of text style transfer and aims to preserve text styles while altering the content. In detail, the input is a set of structured…

Nowadays, scene text recognition has attracted more and more attention due to its diverse applications. Most state-of-the-art methods adopt an encoder-decoder framework with the attention mechanism, autoregressively generating text from…

StyleGANs have shown impressive results on data generation and manipulation in recent years, thanks to its disentangled style latent space. A lot of efforts have been made in inverting a pretrained generator, where an encoder is trained ad…

We propose a Cross-lingual Encoder-Decoder model that simultaneously translates and generates sentences with Semantic Role Labeling annotations in a resource-poor target language. Unlike annotation projection techniques, our model does not…

Recent fast style transfer methods use a pre-trained convolutional neural network as a feature encoder and a perceptual loss network. Although the pre-trained network is used to generate responses of receptive fields effective for…

Neural Text-to-Speech (TTS) systems find broad applications in voice assistants, e-learning, and audiobook creation. The pursuit of modern models, like Diffusion Models (DMs), holds promise for achieving high-fidelity, real-time speech…

Text generator systems have become extremely popular with the advent of recent deep learning models such as encoder-decoder. Controlling the information and style of the generated output without supervision is an important and challenging…

Artistic style transfer is the problem of synthesizing an image with content similar to a given image and style similar to another. Although recent feed-forward neural networks can generate stylized images in real-time, these models produce…

Style transfer aims to fuse the artistic representation of a style image with the structural information of a content image. Existing methods train specific networks or utilize pre-trained models to learn content and style features.…

Text-to-image synthesis has recently seen significant progress thanks to large pretrained language models, large-scale training data, and the introduction of scalable model families such as diffusion and autoregressive models. However, the…

We describe a sequence-to-sequence neural network which directly generates speech waveforms from text inputs. The architecture extends the Tacotron model by incorporating a normalizing flow into the autoregressive decoder loop. Output…