# VANI: Very-lightweight Accent-controllable TTS for Native and Non-native speakers with Identity Preservation

arXiv: https://arxiv.org/abs/2303.07578 · HTML: https://mlsanity.com/paper/2303.07578/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 3 references that are in the map.
- First posted on arXiv 14 Mar 2023.

## Builds on (most cited first, 2 of 2)

- [TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global context](https://mlsanity.com/paper/2110.04410/) (2021)
- [Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech Synthesis](https://mlsanity.com/paper/2005.05957/) (2020)

## Built on by (most cited first, 2 of 2)

- [CrossAccent-TTS: Cross-Lingual Accent-Intensity Controllable Text-to-Speech via Disentangled Speaker and Accent Representations](https://mlsanity.com/paper/2606.25403/) (2026)
- [Scaling NVIDIA's Multi-speaker Multi-lingual TTS Systems with Zero-Shot TTS to Indic Languages](https://mlsanity.com/paper/2401.13851/) (2024)

## Abstract (arXiv)

We introduce VANI, a very lightweight multi-lingual accent controllable speech synthesis system. Our model builds upon disentanglement strategies proposed in RADMMM and supports explicit control of accent, language, speaker and fine-grained F0 and energy features for speech synthesis. We utilize the Indic languages dataset, released for LIMMITS 2023 as part of ICASSP Signal Processing Grand Challenge, to synthesize speech in 3 different languages. Our model supports transferring the language of a speaker while retaining their voice and the native accent of the target language. We utilize the large-parameter RADMMM model for Track 1 and lightweight VANI model for Track 2 and 3 of the competition.