# Enhancing Kurdish Text-to-Speech with Native Corpus Training: A High-Quality WaveGlow Vocoder Approach

arXiv: https://arxiv.org/abs/2409.13734 · HTML: https://mlsanity.com/paper/2409.13734/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 19 references that are in the map.
- First posted on arXiv 10 Sep 2024.

## Builds on (most cited first, 11 of 11)

- [Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions](https://mlsanity.com/paper/1712.05884/) (2017)
- [Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2301.02111/) (2023)
- [WaveGlow: A Flow-based Generative Network for Speech Synthesis](https://mlsanity.com/paper/1811.00002/) (2018)
- [NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Quality](https://mlsanity.com/paper/2205.04421/) (2022)
- [Deep Voice: Real-time Neural Text-to-Speech](https://mlsanity.com/paper/1702.07825/) (2017)
- [WaveFlow: A Compact Flow-based Model for Raw Audio](https://mlsanity.com/paper/1912.01219/) (2019)
- [Towards Building Text-To-Speech Systems for the Next Billion Users](https://mlsanity.com/paper/2211.09536/) (2022)
- [StyleMelGAN: An Efficient High-Fidelity Adversarial Vocoder with Temporal Adaptive Normalization](https://mlsanity.com/paper/2011.01557/) (2020)
- [Breaking Walls: Pioneering Automatic Speech Recognition for Central Kurdish: End-to-End Transformer Paradigm](https://mlsanity.com/paper/2406.02561/) (2024)
- [Ultrasound-based Articulatory-to-Acoustic Mapping with WaveGlow Speech Synthesis](https://mlsanity.com/paper/2008.03152/) (2020)
- [RNN-based speech synthesis using a continuous sinusoidal model](https://mlsanity.com/paper/1904.06075/) (2019)

## Abstract (arXiv)

The ability to synthesize spoken language from text has greatly facilitated access to digital content with the advances in text-to-speech technology. However, effective TTS development for low-resource languages, such as Central Kurdish (CKB), still faces many challenges due mainly to the lack of linguistic information and dedicated resources. In this paper, we improve the Kurdish TTS system based on Tacotron by training the Kurdish WaveGlow vocoder on a 21-hour central Kurdish speech corpus instead of using a pre-trained English vocoder WaveGlow. Vocoder training on the target language corpus is required to accurately and fluently adapt phonetic and prosodic changes in Kurdish language. The effectiveness of these enhancements is that our model is significantly better than the baseline system with English pretrained models. In particular, our adaptive WaveGlow model achieves an impressive MOS of 4.91, which sets a new benchmark for Kurdish speech synthesis. On one hand, this study empowers the advanced features of the TTS system for Central Kurdish, and on the other hand, it opens the doors for other dialects in Kurdish and other related languages to further develop.