mlsanityData to 7 Oct 2026

MnTTS: An Open-Source Mongolian Text-to-Speech Synthesis Dataset and Accompanied Baseline

arXiv 2209.10848 ↗First posted 22 Sep 2022cs.SD cs.AI eess.AScited by 2

Not on the map. Why?

Abstract (arXiv)

This paper introduces a high-quality open-source text-to-speech (TTS) synthesis dataset for Mongolian, a low-resource language spoken by over 10 million people worldwide. The dataset, named MnTTS, consists of about 8 hours of transcribed audio recordings spoken by a 22-year-old professional female Mongolian announcer. It is the first publicly available dataset developed to promote Mongolian TTS applications in both academia and industry. In this paper, we share our experience by describing the dataset development procedures and faced challenges. To demonstrate the reliability of our dataset, we built a powerful non-autoregressive baseline system based on FastSpeech2 model and HiFi-GAN vocoder, and evaluated it using the subjective mean opinion score (MOS) and real time factor (RTF) metrics. Evaluation results show that the powerful baseline system trained on our dataset achieves MOS above 4 and RTF about 3.30×10-1, which makes it applicable for practical use. The dataset, training recipe, and pretrained TTS models are freely available footnotelabelgithuburlhttps://github.com/walker-hyf/MnTTS.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 14 of its 29 references that are in the map. First posted on arXiv 22 Sep 2022.

Builds on

14 of 29 references.

References · 14

  1. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,139
  2. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 800
  3. 2020FastSpeech 2: Fast and High-Quality End-to-End Text to Speechcited by 710
  4. 2019LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speechcited by 639
  5. 2017Tacotron: Towards End-to-End Speech Synthesiscited by 487
  6. 2019MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesiscited by 351
  7. 2021A Survey on Neural Speech Synthesiscited by 182
  8. 2018Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotroncited by 171
  9. 2020AISHELL-3: A Multi-speaker Mandarin TTS Corpus and the Baselinescited by 111
  10. 2017Deep Voice: Real-time Neural Text-to-Speechcited by 83
  11. 2019Almost Unsupervised Text to Speech and Automatic Speech Recognitioncited by 41
  12. 2018Semi-Supervised Training for Improving Data Efficiency in End-to-End Speech Synthesiscited by 30
2 more
  1. 2019End-to-end Text-to-speech for Low-resource Languages by Cross-Lingual Transfer Learningcited by 30
  2. 2020VocGAN: A High-Fidelity Real-time Vocoder with a Hierarchically-nested Adversarial Networkcited by 26

Built on by

Cited by year

Citing papers per year: 2022: 2.

2 papers.

  1. 2022Efficiently Trained Low-Resource Mongolian Text-to-Speech System Based On FullConv-TTScited by 0
  2. 2022MnTTS2: An Open-Source Multi-Speaker Mongolian Text-to-Speech Synthesis Datasetcited by 0