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.
I 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.
This website uses cookies to improve your experience. We'll assume you're ok with this, but you can opt-out if you wish.AcceptRead More
Privacy policy
Privacy Overview
This website uses cookies to improve your experience while you navigate through the website. Out of these, the cookies that are categorized as necessary are stored on your browser as they are essential for the working of basic functionalities of the website. We also use third-party cookies that help us analyze and understand how you use this website. These cookies will be stored in your browser only with your consent. You also have the option to opt-out of these cookies. But opting out of some of these cookies may affect your browsing experience.
Necessary cookies are absolutely essential for the website to function properly. This category only includes cookies that ensures basic functionalities and security features of the website. These cookies do not store any personal information.
Any cookies that may not be particularly necessary for the website to function and is used specifically to collect user personal data via analytics, ads, other embedded contents are termed as non-necessary cookies. It is mandatory to procure user consent prior to running these cookies on your website.