Postscript:
The waveform splicing method has a major disadvantage, that is, the used voice library file is too large and the multi-syllable words cannot be solved.
Another way to implement TTS is to record all Chinese pronunciations, because in Mandarin, there are only1333Type.
Therefore, our voice database only needs to save the 1333 voices without the need to save the pronunciation of each Chinese character.
If the voice database has only 1333 pronunciations, we have to createIndex TableTo record the position of each Chinese Character in the voice database,
With the index table, you can solve the problem of multi-tone Chinese characters. because it involves the recognition of Multi-tone Chinese charactersWord Segmentation technology.
A friend of Takaya asked questions about the natural continuous pronunciation:
To be honest, this is the problem I want to solve and implement most. I thought about it myself. If we use phrases as the language library, the voice
It sounds continuous, because we usually talk in phrases, but if we want to achieve this
The Word Segmentation technology must be used, and the establishment of the language library must be effort-consuming.
For more information about word segmentation, visit http://www.nlp.org.cn /.
White: I have been working on this simple TTS from the programmer's perspective. So many things I have misunderstood or do not understand. I hope my friends can
Don't laugh at me, and help me ask questions and guide me.
There are many other things to be improved in this TTS, such as those listed in the preface. I hope that my friends who like this can work with me to improve it.
Looking forward to ing...
Article introduction:
Introduction to the simplified implementation of Chinese TTS (based on Linux)
Http://blog.csdn.net/dedodong/archive/2006/07/15/923543.aspx
The implementation principle of Simplified Chinese TTS (based on Linux:
Http://blog.csdn.net/dedodong/archive/2006/07/16/927041.aspx
Implementation of a Chinese TTS Language Library Based on Linux
Http://blog.csdn.net/dedodong/archive/2006/08/22/1105742.aspx
A simple implementation of Chinese TTS (based on Linux) for Speech Synthesis
Http://blog.csdn.net/dedodong/archive/2006/08/22/1105879.aspx