Analysis and Synthesis of Hypo and Hyperarticulated Speech
This work addresses speech synthesis for varied articulation degrees, which is incremental as it applies existing HMM-based methods to a new dataset and specific phonetic variations.
The paper tackled the problem of synthesizing hypo and hyperarticulated speech using HMM-based methods, creating a new French database with three articulation degrees and showing that articulation significantly affects acoustic and phonetic features; results indicated that synthesized hypoarticulated speech was less natural than neutral and hyperarticulated versions.
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.