Compact Neural TTS Voices for Accessibility
Abstract
Contemporary text-to-speech solutions for accessibility applications can typically be classified into two categories: (i) device-based statistical parametric speech synthesis (SPSS) or unit selection (USEL) and (ii) cloud-based neural TTS. SPSS and USEL offer low latency and low disk footprint at the expense of naturalness and audio quality. Cloud-based neural TTS systems provide significantly better audio quality and naturalness but regress in terms of latency and responsiveness, rendering these impractical for real-world applications. More recently, neural TTS models were made deployable to run on handheld devices. Nevertheless, latency remains higher than SPSS and USEL, while disk footprint prohibits pre-installation for multiple voices at once. In this work, we describe a high-quality compact neural TTS system achieving latency on the order of 15 ms with low disk footprint. The proposed solution is capable of running on low-power devices.
Keywords
Cite
@article{arxiv.2501.17332,
title = {Compact Neural TTS Voices for Accessibility},
author = {Kunal Jain and Eoin Murphy and Deepanshu Gupta and Jonathan Dyke and Saumya Shah and Vasilieios Tsiaras and Petko Petkov and Alistair Conkie},
journal= {arXiv preprint arXiv:2501.17332},
year = {2025}
}
Comments
Accepted at ICASSP 2025