Scaling NVIDIA's Multi-speaker Multi-lingual TTS Systems with Zero-Shot TTS to Indic Languages
Sound
2024-01-30 v2 Machine Learning
Audio and Speech Processing
Abstract
In this paper, we describe the TTS models developed by NVIDIA for the MMITS-VC (Multi-speaker, Multi-lingual Indic TTS with Voice Cloning) 2024 Challenge. In Tracks 1 and 2, we utilize RAD-MMM to perform few-shot TTS by training additionally on 5 minutes of target speaker data. In Track 3, we utilize P-Flow to perform zero-shot TTS by training on the challenge dataset as well as external datasets. We use HiFi-GAN vocoders for all submissions. RAD-MMM performs competitively on Tracks 1 and 2, while P-Flow ranks first on Track 3, with mean opinion score (MOS) 4.4 and speaker similarity score (SMOS) of 3.62.
Keywords
Cite
@article{arxiv.2401.13851,
title = {Scaling NVIDIA's Multi-speaker Multi-lingual TTS Systems with Zero-Shot TTS to Indic Languages},
author = {Akshit Arora and Rohan Badlani and Sungwon Kim and Rafael Valle and Bryan Catanzaro},
journal= {arXiv preprint arXiv:2401.13851},
year = {2024}
}
Comments
Presentation accepted at ICASSP 2024