# Unsupervised Polyglot Text To Speech

## TL;DR

This paper introduces an unsupervised, multilingual neural TTS system capable of voice transfer across languages without requiring parallel data, demonstrating effective speaker identity preservation and language conversion.

## Contribution

It presents a novel unsupervised polyglot neural TTS model with multiple sub-networks and identity preservation, enabling cross-language voice transfer without parallel training data.

## Key findings

- Effective voice transfer across three languages
- Preserves speaker identity in multiple languages
- Works with over 400 speakers without parallel data

## Abstract

We present a TTS neural network that is able to produce speech in multiple languages. The proposed network is able to transfer a voice, which was presented as a sample in a source language, into one of several target languages. Training is done without using matching or parallel data, i.e., without samples of the same speaker in multiple languages, making the method much more applicable. The conversion is based on learning a polyglot network that has multiple per-language sub-networks and adding loss terms that preserve the speaker's identity in multiple languages. We evaluate the proposed polyglot neural network for three languages with a total of more than 400 speakers and demonstrate convincing conversion capabilities.