TITLE:
Emotional Speech Synthesis Based on Prosodic Feature Modification
AUTHORS:
Ling He, Hua Huang, Margaret Lech
KEYWORDS:
Emotional Speech Synthesis; Prosodic Features; Time Domain Pitch Synchronous Overlap Add
JOURNAL NAME:
Engineering,
Vol.5 No.10B,
October
25,
2013
ABSTRACT:
The synthesis of emotional speech has wide applications
in the field of human-computer interaction, medicine, industry and so on. In
this work, an emotional speech synthesis system is proposed based on prosodic
features modification and Time Domain Pitch Synchronous OverLap Add (TD-PSOLA)
waveform concatenative algorithm. The system produces synthesized speech with
four types of emotion: angry, happy, sad and bored. The experiment results show
that the proposed emotional speech synthesis system achieves a good performance.
The produced utterances present clear emotional expression. The
subjective test reaches high classification accuracy for different types of
synthesized emotional speech utterances.