# Fast and small footprint Hybrid HMM-HiFiGAN based system for speech synthesis in Indian languages

arXiv: https://arxiv.org/abs/2302.06227 · HTML: https://mlsanity.com/paper/2302.06227/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Feb 2023.

## Built on by (most cited first, 1 of 1)

- [Compression of end-to-end non-autoregressive image-to-speech system for low-resourced devices](https://mlsanity.com/paper/2312.00174/) (2023)

## Abstract (arXiv)

Hidden-Markov-model (HMM) based text-to-speech (HTS) offers flexibility in speaking styles along with fast training and synthesis while being computationally less intense. HTS performs well even in low-resource scenarios. The primary drawback is that the voice quality is poor compared to that of E2E systems. A hybrid approach combining HMM-based feature generation and neural-network-based HiFi-GAN vocoder to improve HTS synthesis quality is proposed. HTS is trained on high-resolution mel-spectrograms instead of conventional mel generalized coefficients (MGC), and the output mel-spectrogram corresponding to the input text is used in a HiFi-GAN vocoder trained on Indic languages, to produce naturalness that is equivalent to that of E2E systems, as evidenced from the DMOS and PC tests.