Comprehensive Evaluation Of Statistical Speech Waveform Synthesis

Abstract

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.

Stats

• citations4
• S2 citations—
• github stars0
• HF likes0
• heat score5.24
• arxiv keymerritt2018comprehensive

Related papers

• Evaluating Text-to-speech Synthesis From A Large Discrete Token-based Speech Language Model (2024)0.00
• Objective Evaluation Of Prosody And Intelligibility In Speech Synthesis Via Conditional Prediction Of Discrete Tokens (2025)0.00
• A Comparison Of Vietnamese Statistical Parametric Speech Synthesis Systems (2020)0.00
• Naturalspeech: End-to-end Text To Speech Synthesis With Human-level Quality (2022)16.32
• Evaluating And Reducing The Distance Between Synthetic And Real Speech Distributions (2022)0.00
• An Experimental Study: Assessing The Combined Framework Of Wavlm And BEST-RQ For Text-to-speech Synthesis (2023)0.00
• Comparison Of Speech Representations For Automatic Quality Estimation In Multi-speaker Text-to-speech Synthesis (2020)0.00
• A Text-to-speech Pipeline, Evaluation Methodology, And Initial Fine-tuning Results For Child Speech Synthesis (2022)10.21