Objectives
...
Combine
...
Sound +Vision = Sound feedback for interface changes
Speech + Text = Include speech to text to text to speech
Vision + Speech = Imagined speech
...
Simplify
...
Platform = Make it more accessible for the user
Visual = Minimum viable visuals
Content = Divide the content into understandable sections
...
Amplify
...
Text = Highlight text
Content = Highlight the text being red
Display = Function buttons on page
Function = Have speech do more than just the text
...
Minimize
...
Keys = Less keys with more functions
Function = Divide options to advanced and visible
...
Modify
...
Content = Language
Voice+content = Have different speech tone / speed / accent, for different content
...
Isolate
...
Hearing = Noise reduction
User
Issues
- Natural and pleasant to listen to
- Most speech synthesis have a neutral, one-size-fits-all expression, regardless of what it's saying.
- Expressions, expressive vs. unexpressive
- Language
- The voices are weird
Concerns
- What impact could the author have when using TTS?
- Language translation
- Frequency of Software Usage
user analysis
- difficulties with language processing
- problems decoding words/text
- comprehension difficulties
- cannot read grade-level text