Forum Replies Created
-
AuthorPosts
-
I don’t understand why we need to keep iteratively doing dynamic realignment with the Viterbi algorithm after we have updated the model parameters.
That works, but now I need to capture that value so I can manipulate it. I don’t really understand how to do that in the shell?
But how do I make
train.scp
? Do I have to write it by hand?Following up on that, would it be enough to test one hypothesis about naturalness and one hypothesis about intelligibility, using a formal listening test?
For example: Hypothesis 1 makes a prediction about the relative naturalness of an ARCTIC-A voice and a domain-specific voice; Hypothesis 2 makes a prediction about the effect on intelligibility of changing some other system component or design decision.
March 3, 2018 at 10:51 in reply to: Amount of source text to start with, for my text selection algorithm #9130I wanted to create a domain-specific voice. Originally, I wanted to do a text selection algorithm for this that would ensure proper diphone coverage, but I am having trouble getting enough data for that without compromising the specificity of my domain.
I have about 550 domain-specific phrases, but I haven’t checked their diphone distribution. I was thinking of having an experiment where I compare domain-specific and non-domain-specific phrases using this voice. My question is, is it acceptable to use this material as is instead of doing a text selection algorithm for it based on diphone coverage?
In this case I would also run a separate experiment specifically about the effects of diphone coverage that uses a large amount of non-domain specific data because I do want to try implementing this algorithm.
I understand that this would require a lot of recording time, but that’s fine with me and my partner.
What pre-processing and post-processing is used in
pda
. We must specify male/female pitch range: would that count as post-processing?Which variant of the autocorrelation function does Festival use (there are many listed in the Talkin paper…)?
I was wondering why 8bits and 16bits are used normally. I mean, will something go wrong if we choose 9-15bits?
Absolutely! Can I be in it please?
-
This reply was modified 9 years, 5 months ago by
Simon.
-
This reply was modified 9 years, 5 months ago by
-
AuthorPosts