Multilingual Text-to-Speech Synthesis for Turkic Languages Using Transliteration

Rustem Yeshpanov, Saida Mussakhojayeva, Yerbolat Khassanov
5/25/2023
eess.AScs.CL

No official code found. Best implementation: IS2AI/TurkicTTS (84 stars, last commit 2023-08-21).

Abstract

This work aims to build a multilingual text-to-speech (TTS) synthesis system for ten lower-resourced Turkic languages: Azerbaijani, Bashkir, Kazakh, Kyrgyz, Sakha, Tatar, Turkish, Turkmen, Uyghur, and Uzbek. We specifically target the zero-shot learning scenario, where a TTS model trained using the data of one language is applied to synthesise speech for other, unseen languages. An end-to-end TTS system based on the Tacotron 2 architecture was trained using only the available data of the Kazakh language. To generate speech for the other Turkic languages, we first mapped the letters of the Turkic alphabets onto the symbols of the International Phonetic Alphabet (IPA), which were then converted to the Kazakh alphabet letters. To demonstrate the feasibility of the proposed approach, we evaluated the multilingual Turkic TTS model subjectively and obtained promising results. To enable replication of the experiments, we make our code and dataset publicly available in our GitHub repository.

View on arXivView PDF

Code Implementations(1)

IS2AI/TurkicTTSCommunity100%

A multilingual text-to-speech synthesis system for ten lower-resourced Turkic languages: Azerbaijani, Bashkir, Kazakh, Kyrgyz, Sakha, Tatar, Turkish, Turkmen, Uyghur, and Uzbek.

849PythonOct 27, 20223 years ago
ipalower-resourcedtransliterationttsturkic+1 more

Similar Papers

Learning to Speak from Text: Zero-Shot Multilingual Text-to-Speech with Unsupervised Text Pretraining

88% match1 repo652023

Textless Unit-to-Unit training for Many-to-Many Multilingual Speech-to-Speech Translation

87% match1 repo312023

Meta Learning Text-to-Speech Synthesis in over 7000 Languages

86% match1 repo2.2k2024

Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling

85% match2023

Giving Voice to the Constitution: Low-Resource Text-to-Speech for Quechua and Spanish Using a Bilingual Legal Corpus

84% match2026

Zero-AVSR: Zero-Shot Audio-Visual Speech Recognition with LLMs by Learning Language-Agnostic Speech Representations

84% match1 repo362025

Cite this paper

@article{yeshpanov2023multilingual,
  title  = {Multilingual Text-to-Speech Synthesis for Turkic Languages Using Transliteration},
  author = {Rustem Yeshpanov and Saida Mussakhojayeva and Yerbolat Khassanov},
  year   = {2023},
  eprint = {2305.15749},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2305.15749v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2305.15749.svg)](https://codeofpaper.com/paper/2305.15749)

Discussion