StAyaL | Multilingual Style Transfer

TL;DR

This paper introduces a novel multilingual style transfer method that captures individual speaker styles using minimal data and enables style transfer across languages, enhancing personalized and cross-linguistic communication.

Contribution

It presents a new approach leveraging high-dimensional embeddings from limited data to perform style transfer and translation across multiple languages.

Findings

Achieved 74.9% test accuracy in style transfer tasks.

Demonstrated topic-agnostic style transfer with high F1 score.

Enabled style transfer with only 100 lines of data per individual.

Abstract

Stylistic text generation plays a vital role in enhancing communication by reflecting the nuances of individual expression. This paper presents a novel approach for generating text in a specific speaker's style across different languages. We show that by leveraging only 100 lines of text, an individuals unique style can be captured as a high-dimensional embedding, which can be used for both text generation and stylistic translation. This methodology breaks down the language barrier by transferring the style of a speaker between languages. The paper is structured into three main phases: augmenting the speaker's data with stylistically consistent external sources, separating style from content using machine learning and deep learning techniques, and generating an abstract style profile by mean pooling the learned embeddings. The proposed approach is shown to be topic-agnostic, with test accuracy and F1 scores of 74.9% and 0.75, respectively. The results demonstrate the potential of the style profile for multilingual communication, paving the way for further applications in personalized content generation and cross-linguistic stylistic transfer.