# Unsupervised Polyglot Text To Speech

arXiv: https://arxiv.org/abs/1902.02263 · HTML: https://mlsanity.com/paper/1902.02263/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Feb 2019.

## Built on by (most cited first, 10 of 10)

- [Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling](https://mlsanity.com/paper/2303.03926/) (2023)
- [Multilingual Byte2Speech Models for Scalable Low-resource Speech Synthesis](https://mlsanity.com/paper/2103.03541/) (2021)
- [Cross-Lingual Text-to-Speech Using Multi-Task Learning and Speaker Classifier Joint Training](https://mlsanity.com/paper/2201.08124/) (2022)
- [Unify and Conquer: How Phonetic Feature Representation Affects Polyglot Text-To-Speech (TTS)](https://mlsanity.com/paper/2207.01547/) (2022)
- [Mix and Match: An Empirical Study on Training Corpus Composition for Polyglot Text-To-Speech (TTS)](https://mlsanity.com/paper/2207.01507/) (2022)
- [Multilingual Multiaccented Multispeaker TTS with RADTTS](https://mlsanity.com/paper/2301.10335/) (2023)
- [Improve Bilingual TTS Using Dynamic Language and Phonology Embedding](https://mlsanity.com/paper/2212.03435/) (2022)
- [Data-augmented cross-lingual synthesis in a teacher-student framework](https://mlsanity.com/paper/2204.00061/) (2022)
- [Cross-lingual Knowledge Distillation via Flow-based Voice Conversion for Robust Polyglot Text-To-Speech](https://mlsanity.com/paper/2309.08255/) (2023)
- [Unseen Speaker and Language Adaptation for Lightweight Text-To-Speech with Adapters](https://mlsanity.com/paper/2508.18006/) (2025)

## Abstract (arXiv)

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.