| 摘要 |
A typical TTS system converts text to speech and analyses normalised text morphologically and syntactically to determine the words or morphological tokens and the syntax of those words into notation which represents the pronunciation. In the prior art, a pronunciation module 6 of the TTS system determines whether the word or token is present in a dictionary 2 and if so obtains the pronunciation but if not then applies pronunciation rules to determine the pronunciation and stores the word in an exceptions log 4. The present invention relates to adapting the contents of the dictionary 2 by adding from the log 4 those words most frequently used and deleting from the dictionary 2 those words which are less frequently used. The present invention is particularly advantageous in those instances where memory size is restricted such as in mobile phones, mobile computers and digital still cameras. Pronunciation of words added to the dictionary may be obtained from a user or from a remote dictionary. |
