Qt To Get Possible Speech Recognition API

[phoronix]

Phoronix: Qt To Get Possible Speech Recognition API

Following this week's Qt 5.6 Alpha release is some more exciting news for this open-source toolkit...

http://www.phoronix.com/scan.php?page=news_item&px=Qt-Speech-Recognition

[Michael_S]

I think this is excellent, for two reasons:

1. One of the areas that Apple and Microsoft occasionally do have an edge over free software is in support for users with disabilities. Any project like this helps free software bring that back to parity.

2. I fear free software stands the most to lose in the next decade to people who love the convenience of "Ok, Google", Siri, Cortana, and Amazon Echo's Alexa. With this feature and projects like Mycroft, maybe we can even the playing field and I can use Linux and maybe someday Firefox OS or Replicant without letting some soulless corporation hear everything I do all day long.

[Michael_S]

Weird - I wrote a response, and it seemed to vanish. Maybe it's a fluke at Phoronix, or maybe it's a problem with Firefox Nightly (which I'm running).

I think this is great, for two reasons:
1. Accessibility for disabled users is one place where free software often trails the proprietary vendors. This isn't surprising - Apple and Microsoft do the right thing here because their corrupt models leave them with billions to spend.
2. The convenience of Google Now, Siri, Cortana, and Alexa is probably the biggest danger to free software adoption going forward. If projects like this and like Mycroft bring decent voice recognition free software into existence, we can level the playing field and users can have the convenience of the proprietary voice recognition applications without the invasion of privacy.

[carewolf]

This appears to only be API. You will likely still need proprietary software for the backend. Unless there is an open source speech recognizition backend out there?

[TheBlackCat]

This appears to only be API. You will likely still need proprietary software for the backend. Unless there is an open source speech recognizition backend out there?

Sphinx and Julius are open-source speech recognition backends.