Perceptual Effects of the Degree of Articulation in HMM-based Speech Synthesis

This paper focuses on the understanding of the effects leading to high-quality HMM-based speech synthesis with various degrees of articulation. The adaptation of a neutral speech synthesizer to generate hypo and hyperarticulated speech is first performed. The impact of cepstral adaptation, of prosody, of phonetic transcription as well as the adaptation technique on the perceived degree of articulation is studied. For this, a subjective evaluation is conducted. It is shown that high-quality hypo and hyperarticulated speech synthesis requires the use of an efficient adaptation such as CMLLR. Moreover, in addition to prosody adaptation, the importance of cepstrum adaptation as well as the use of a Natural Language Processor able to generate realistic hypo and hyper-articulated phonetic transcriptions is assessed.