Clustering of duration patterns in speech for Text-to-Speech Synthesis

摘要

Synthesis of natural sounding speech is the greatest challenge in a Text-to-Speech Synthesis (TTS) system. In natural speech, duration, intensity and pitch are dynamically varied which is manifested as rhythm or prosody of speech. If these variations are not recreated, the synthesized speech will sound robotic. Synthesis of good quality speech depends on how well the duration and intonation patterns are imposed on speech segments. The best way to improve naturalness in speech is to mimic the way human brain imposes rhythm. We speak in a particular style by varying the duration of the speech segments in words and phrases as per certain specific duration patterns. Brain might be retrieving the corresponding patterns at the time of speaking for generating a discourse in a particular style (news reading, bible reading, story telling etc.). The main objective of this work is to investigate the existence of duration patterns in natural speech using cluster analysis. Speech uttered in Malayalam, an Indian language was taken for analysis. Cluster analysis was done on isolated words, as well as on words and phrases in continuous speech. Results of cluster analysis when observed using silhouette plot showed the existence of duration patterns in speech.