KazakhTTS: An Open-Source Kazakh Text-to-Speech Synthesis Dataset

Abstract

This paper introduces a high-quality open-source speech synthesis dataset for Kazakh, a low-resource language spoken by over 13 million people worldwide. The dataset consists of about 93 hours of transcribed audio recordings spoken by two professional speakers (female and male). It is the first publicly available large-scale dataset developed to promote Kazakh text-to-speech (TTS) applications in both academia and industry. In this paper, we share our experience by describing the dataset development procedures and faced challenges, and discuss important future directions. To demonstrate the reliability of our dataset, we built baseline end-to-end TTS models and evaluated them using the subjective mean opinion score (MOS) measure. Evaluation results show that the best TTS models trained on our dataset achieve MOS above 4 for both speakers, which makes them applicable for practical use. The dataset, training recipe, and pretrained TTS models are freely available.

arXiv comment5 pages, 4 tables, 2 figures, accepted to INTERSPEECH 2021

References in corpus (6)

• Adam: A Method for Stochastic Optimization
• WaveNet: A Generative Model for Raw Audio
• FastSpeech: Fast, Robust and Controllable Text to Speech
• Deep Voice: Real-time Neural Text-to-Speech
• AISHELL-3: A Multi-speaker Mandarin TTS Corpus and the Baselines
• Almost Unsupervised Text to Speech and Automatic Speech Recognition

Cited by in corpus (2)

• A Survey on Neural Speech Synthesis
• A Study of Multilingual End-to-End Speech Recognition for Kazakh, Russian, and English