Mapping systems prosodic templates for text conversion into speech.

摘要

A method of generating prosody for use in the synthesis of text into speech, comprising the steps of information: receiving a chain (30) input text and determining a pattern of features (14) prosodic associated with the chain (30) input text, identifying a first template (18, 28) prosodic from a prosodic plurality of templates (10) where each prosody template represents a pattern of prosodic features that may be associated with a text string and having the first prosody template pattern prosodic characteristics correlate with the input text string; characterized by replicating a part of the first group (76, 78) when the prosodic pattern for the first prosody template is shorter than the pattern for the input text strings; and concatenating the replicated portion of the first prosody template onto the pattern of the first group (76, 78) thereby constructing one prosodic generated prosody template that more closely correlates to the input text string.