# Comprehensive evaluation of statistical speech waveform synthesis

arXiv: https://arxiv.org/abs/1811.06296 · HTML: https://mlsanity.com/paper/1811.06296/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Nov 2018.

## Built on by (most cited first, 3 of 3)

- [Rethinking MUSHRA: Addressing Modern Challenges in Text-to-Speech Evaluation](https://mlsanity.com/paper/2411.12719/) (2024)
- [Mix and Match: An Empirical Study on Training Corpus Composition for Polyglot Text-To-Speech (TTS)](https://mlsanity.com/paper/2207.01507/) (2022)
- [Creating New Voices using Normalizing Flows](https://mlsanity.com/paper/2312.14569/) (2023)

## Abstract (arXiv)

Statistical TTS systems that directly predict the speech waveform have recently reported improvements in synthesis quality. This investigation evaluates Amazon's statistical speech waveform synthesis (SSWS) system. An in-depth evaluation of SSWS is conducted across a number of domains to better understand the consistency in quality. The results of this evaluation are validated by repeating the procedure on a separate group of testers. Finally, an analysis of the nature of speech errors of SSWS compared to hybrid unit selection synthesis is conducted to identify the strengths and weaknesses of SSWS. Having a deeper insight into SSWS allows us to better define the focus of future work to improve this new technology.