SYSTEM AND METHOD FOR SYNTHESIS OF SPEECH FROM PROVIDED TEXT

摘要

A system and method are presented for the synthesis of speech from provided text. Particularly, the generation of parameters within the system is performed as a continuous approximation in order to mimic the natural flow of speech as opposed to a step-wise approximation of the feature stream. Provided text may be partitioned and parameters generated using a speech model. The generated parameters from the speech model may then be used in a post-processing step to obtain a new set of parameters for application in speech synthesis.

主权项

1. A system for synthesizing speech for provided text comprising:
a. means for generating context labels for said provided text; b. means for generating a set of parameters for the context labels generated for said provided text using a speech model; c. means for processing said generated set of parameters, wherein said means for processing is capable of variance scaling; and d. means for synthesizing speech for said provided text, wherein said means for synthesizing speech is capable of applying the processed set of parameters to synthesizing speech.