How does the algorithm handle words that do not have a fixed number of syllables: child, fire, ........... ?
It's a bit chicken-and-egg. The plan is that a first-pass will check to see if the poem is close to a form. If it is, a second-pass will adjust the syllables to see if a closer match can be obtained.
Or words that change pronunciation based on context: the for a quick instance? And then, the big ones, pause and accent? - The text-to-sound convertor can be replaced by the user, but even so, it'll get things wrong. Users will be able to tweak the output. The stress-detection is also prone to error.
|