We are an important publisher of English language learning material looking to develop a server-side app which will compare user input from a mic against a number of possible utterances and return a hi or lo probaility (or +ve and -ve response). Example:
User hears (doesn't need developing) 'What do you think of my new skirt?'
User can choose to respond:
a) I think it looks great.
b) I don’t think it’s mine.
c) I just can’t think.
d) I never wear skirts.
Only (a) is correct. If users responds (a)then will be permitted to continue to next exchange where they hear 'Does it go with my shoes?'
and can then respond:
a) Your shoes are there.
b) Well, not really.
c) Yes, it’s gone.
d) It’s the wrong size.
only (b) is correct
Tolerance of bad pronunciation should be high. We already have a dataset of 38 typical users recording all utterances.
Looking to start asap. Would prefer developers in Europe. 3-month job we reckon?
Pls contact rick.shep@gmail.com
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
We are an important publisher of English language learning material looking to develop a server-side app which will compare user input from a mic against a number of possible utterances and return a hi or lo probaility (or +ve and -ve response). Example:
User hears (doesn't need developing) 'What do you think of my new skirt?'
User can choose to respond:
a) I think it looks great.
b) I don’t think it’s mine.
c) I just can’t think.
d) I never wear skirts.
Only (a) is correct. If users responds (a)then will be permitted to continue to next exchange where they hear 'Does it go with my shoes?'
and can then respond:
a) Your shoes are there.
b) Well, not really.
c) Yes, it’s gone.
d) It’s the wrong size.
only (b) is correct
Tolerance of bad pronunciation should be high. We already have a dataset of 38 typical users recording all utterances.
Looking to start asap. Would prefer developers in Europe. 3-month job we reckon?
Pls contact rick.shep@gmail.com