Analysis and Synthesis of Hypo and Hyperarticulated Speech

TL;DR

This study analyzes and synthesizes hypo and hyperarticulated speech using HMM-based methods, revealing significant articulatory differences and evaluating the naturalness of synthesized speech through objective and subjective tests.

Contribution

Introduces a new French database with different articulation levels and demonstrates the impact of articulation on speech characteristics and synthesis quality.

Findings

Articulation levels significantly affect vocal and phonetic features.

Synthesized hypoarticulated speech is less natural than neutral and hyperarticulated speech.

Objective and subjective tests assess the quality of synthesized speech.

Abstract

This paper focuses on the analysis and synthesis of hypo and hyperarticulated speech in the framework of HMM-based speech synthesis. First of all, a new French database matching our needs was created, which contains three identical sets, pronounced with three different degrees of articulation: neutral, hypo and hyperarticulated speech. On that basis, acoustic and phonetic analyses were performed. It is shown that the degrees of articulation significantly influence, on one hand, both vocal tract and glottal characteristics, and on the other hand, speech rate, phone durations, phone variations and the presence of glottal stops. Finally, neutral, hypo and hyperarticulated speech are synthesized using HMM-based speech synthesis and both objective and subjective tests aiming at assessing the generated speech quality are performed. These tests show that synthesized hypoarticulated speech seems to be less naturally rendered than neutral and hyperarticulated speech.