Related papers: Learning to Generate Multiple Style Transfer Outpu…

Text generation aims to produce human-like natural language output for down-stream tasks. It covers a wide range of applications like machine translation, document summarization, dialogue generation and so on. Recently deep neural…

Controllable generative sequence models with the capability to extract and replicate the style of specific examples enable many applications, including narrating audiobooks in different voices, auto-completing and auto-correcting written…

Text-to-image model personalization aims to introduce a user-provided concept to the model, allowing its synthesis in diverse contexts. However, current methods primarily focus on the case of learning a single concept from multiple images…

Unsupervised style transfer models are mainly based on an inductive learning approach, which represents the style as embeddings, decoder parameters, or discriminator parameters and directly applies these general rules to the test cases.…

Different people speak with diverse personalized speaking styles. Although existing one-shot talking head methods have made significant progress in lip sync, natural facial expressions, and stable head motions, they still cannot generate…

Recently, style transfer has received a lot of attention. While much of this research has aimed at speeding up processing, the approaches are still lacking from a principled, art historical standpoint: a style is more than just a single…

Large-scale noisy web image-text datasets have been proven to be efficient for learning robust vision-language models. However, when transferring them to the task of video retrieval, models still need to be fine-tuned on hand-curated paired…

We address the problem of cross-speaker style transfer for text-to-speech (TTS) using data augmentation via voice conversion. We assume to have a corpus of neutral non-expressive data from a target speaker and supporting conversational…

Learning to generate fluent natural language from structured data with neural networks has become an common approach for NLG. This problem can be challenging when the form of the structured data varies between examples. This paper presents…

We introduce ReStyle3D, a novel framework for scene-level appearance transfer from a single style image to a real-world scene represented by multiple views. The method combines explicit semantic correspondences with multi-view consistency…

Neural text-to-speech synthesis (NTTS) models have shown significant progress in generating high-quality speech, however they require a large quantity of training data. This makes creating models for multiple styles expensive and…

Deep generative models are now able to synthesize high-quality audio signals, shifting the critical aspect in their development from audio quality to control capabilities. Although text-to-music generation is getting largely adopted by the…

Recent work in neural generation has attracted significant interest in controlling the form of text, such as style, persona, and politeness. However, there has been less work on controlling neural text generation for content. This paper…

We present an easy and efficient method to extend existing sentence embedding models to new languages. This allows to create multilingual versions from previously monolingual models. The training is based on the idea that a translated…

A latent-variable model is introduced for text matching, inferring sentence representations by jointly optimizing generative and discriminative objectives. To alleviate typical optimization challenges in latent-variable models for text, we…

Style transfer TTS has shown impressive performance in recent years. However, style control is often restricted to systems built on expressive speech recordings with discrete style categories. In practical situations, users may be…

We present a new dataset with the goal of advancing image style transfer - the task of rendering one image in the style of another image. The dataset covers various content and style images of different size and contains 10.000 stylizations…

We present a generative model for multitask conditional language generation. Our guiding hypothesis is that a shared set of latent skills underlies many disparate language generation tasks, and that explicitly modelling these skills in a…

Sentiment transfer is one popular example of a text style transfer task, where the goal is to reverse the sentiment polarity of a text. With a sentiment reversal comes also a reversal in meaning. We introduce a different but related task…

Style transfer has been widely applied to give real-world images a new artistic look. However, given a stylized image, the attempts to use typical style transfer methods for de-stylization or transferring it again into another style usually…