Hi all,
Which information in the labels are optional and which of them are required?
for example can we skip the B section(setting b1,b2,... to zero) without significantly decreasing the quality of synthesized speech?
I am writing a text analyzer to build labels for HTS from raw text, and i want to know that which information MUST be extracted and which of them aren't so important.
It seems that only the A and P section (current phoneme, previous phoneme , ...) has an direct effect on the general quality of synthesized speech??