Altruistic Research for Smartphone vs Dialects

+Mary Wright Layton has recently posted about her final project examining dialects and smartphones. You can read that here. I was really intrigued by this idea that maybe voice activated technology do favor certain languages and accents over others. To help out, I dived a bit deeper into the technology that goes behind voice activation and did some linguistic research. Hope this helps!

Under the eBooks search on the Lee Library site, I found this Google Book called Psychology Study Guide for Smartphones and Mobile Devices that talks about how "making a principled distinction between one language and another is usually impossible." It gives examples of how some dialects are similar to one another like German and Dutch, or Spanish and Italian. The similarities between dialects means "the transition between languages within the same language family is sometimes gradual" (under subheading Human Languages). It also mentions the phoneme of languages. The Google definition of phoneme: any of the perceptually distinct units of sound in a specified language that distinguish one word from another, like p, d, and t in pad vs pat. So when we look at dialects, which languages have spelling that also corresponds to how it's pronounced? Which languages are easy to guess spelling, but not pronunciation? Which languages have difficult spelling and pronunciation? I think in terms of your final topic, Mary could look at how the phonemes of languages changes the likelihood of a smartphone or any voice activation device understanding what is being said.

I also went through JSTOR just for kicks and found two articles Mary might be interested in. They are all a bit dated, but I think the concepts are still worth exploring. The first one here also has a subheading about speech recognition problems. It does point out the advancements that have been made so far with the technology though (by so far, it means in the last ten years from 1995). If we've made that many improvements so far, hopefully today there's work going into making it better now. This article explores how Spanish Dialectology is being taught with digital audio technology. Not exactly the same as voice recognition, but there are technologies out there working on different dialects that perhaps smartphones don't employ as successfully yet.

As for how the technology itself works, I did a quick Google search on "voice recognition technology" and found this quick explanation of how it works. You can read that here.

I know in your post you mentioned the Dragon software. Looking at Google+ articles under "voice activation" search I found a few people talking about Snapdragon and OK Google. I'm not sure if they're necessarily better than the Dragon software; however, but it may be a good idea to compare different software to see if there are apps better at listening to more/different dialects than others.

Good luck with your final project! And it's great that you've already got some social proof going on with the director of the International Student Association! Hope you get back plenty of results from there.