Kickstart a free reading and pronunciation game

James Salsman sez, "I've been working for decades on a free speech recognition-based game to teach English reading and pronunciation, and this year it is going to happen, thanks to Google's Summer of Code and the One Laptop Per Child contributors' program. But to make it really useful (and on as many mobile devices as possible) we need to raise just a little more money. We have secured funding for two of the three other engineers who want to help finish the project, but we still need to money for the third and to collect sufficient exemplar pronunciation recordings and create engaging graphics, animations, and game content to support English learners of all ages and experience levels. Please help!" Here's his Kickstarter.
Discuss

6 Responses to “Kickstart a free reading and pronunciation game”

  1. ZenMonkey says:

    …except for deaf kids and some others with special needs. It does sound like a great project but my money goes to accessibility.

  2. Thanks, Cory! I’m James Salsman, the project mentor/leader. Ask me anything!

  3. BillStewart2012 says:

    I’ve seen some of James’s previous work (Hi, James!), and it’s been really cool stuff, with a focus on giving people practical, friendly tools to improve their language skills.  It’ll be interesting to see how far he can go with this if he can get his team funded.

  4. MetalSamurai says:

    Uh, wait. “English” pronunciation?

    Do you mean American? Or RP? Or Yorkshire, Scouse, Geordie, Welsh, Cockney?

    I don’t envy anyone trying to learn this crazy language as a second language:

    http://www.thepoke.co.uk/2011/12/23/english-pronunciation/

    That’s before we get into vicious battles about scone vs scone or the southern nonsense that “scarf” rhymes with “giraffe”.

    • James Salsman says:

      MetalSamurai,

      The fundraiser is in part so we can afford to use mturk.com to collect as many widely varied accents as possible, to classify students by which they seem to be speaking and score them in relation to the exemplar pronunciations from speakers with the same accents. If we don’t make the fundraiser goals, we will be stuck releasing much less content probably in only American Midwestern accents.  

      I also tried to answer this in the Kickstarter FAQ at http://www.kickstarter.com/projects/jsalsman/choose-your-reading-and-pronunciation-adventure#WhatAcceAreYouGoinToRecoAsCorr

      “If we make our funding goal we will have enough money to collect a statistically significant number of exemplar recordings in Standard American, Southern American, British, and Australian English accent pronunciations of each phrase in the database.  That will allow us to correctly score any of those (including mixtures of them, which is odd but doesn’t cause problems in practice) while rejecting pronunciations that do not match one of those accents.

      “If we don’t reach our funding goals, we will probably end up with content limited to Standard American English accents, and a lot less of it.

      “Dialects are a bit trickier. We aren’t planning to support, for example, Scottish and British English dialects comprised of outright vocabulary variations (e.g. using “lorry” for “truck”) but anyone willing to code the alternative phonetic dictionary entries and collect sufficient pronunciation exemplar data (whether using Mechanical Turk or not) can certainly make a database compatible with other dialects, too.”

  5. Chris Leonard says:

    ZenMonkey FWIW, the Sugar UI for the OLPC XO laptop has added text-to-speech for vision-impaired accessibility, and we are working on about 130 languages in our translation database.

Leave a Reply