Help train Mozilla's open source voice recognition

Help train Mozilla's open source voice recognition

Postby Julius » 18 Jul 2017, 15:23

See:
https://voice.mozilla.org/
very easy to use and potentially a very useful thing to have as an open-source model.
“You never change things by fighting the existing reality. To change something, build a new model that makes the existing model obsolete” - Buckminster Fuller
User avatar
Julius
Community Moderator
 
Posts: 2142
Joined: 06 Dec 2009, 14:02

Re: Help train Mozilla's open source voice recognition

Postby eugeneloza » 19 Jul 2017, 09:01

Fantastic!
However, I couldn't find neither feedback, nor my question answered in FAQ.
They do not list post-USSR countries in accent selection :) Neither preference in sound quality (I can record by both webcam audio and by semi-professional studio equipment). Also there are no guides for reading, e.g. should it be as neutral as possible, or with some artistic feel to it? Well, actually those are not too important, but might make the audition a bit better.

To everybody:
Recording your voice is not the only way to easily help the engine. You may just listen and mark other's auditions as valid, `cause it's damn hell of manual work.
User avatar
eugeneloza
 
Posts: 490
Joined: 22 Aug 2014, 12:15
Location: Ukraine

Re: Help train Mozilla's open source voice recognition

Postby Julius » 19 Jul 2017, 09:34

Yeah, the website is a bit focussed on English accents, while the reality is that the English voice recognition will also be used by a lot of non-native speakers. I wouldn’t worry about it too much, as in the end it will help the machine learning framework to better understand non-native voices. There are also already quite a few obviously non-native speakers if you listen to the sentences. Same goes for recording quality... it should in fact be non-perfect samples so that the system can better distinguish between background and recording noises and the actual voice. So by all means, use you web-cam and not your professional equipment.

However, what I am a bit concerned about is that they chose "book reading" examples. Somehow people have different and more intentionally pronounced voices when they read stories from a book, and this becomes very evident in the recorded samples. I am not an expert on voice recognition, but it would seem to me that this will somewhat distort the ML model towards this kind of task and that it will not work so well with the actual more common use-case of voice commands or transcription of natural conversations.
“You never change things by fighting the existing reality. To change something, build a new model that makes the existing model obsolete” - Buckminster Fuller
User avatar
Julius
Community Moderator
 
Posts: 2142
Joined: 06 Dec 2009, 14:02

Re: Help train Mozilla's open source voice recognition

Postby eugeneloza » 19 Jul 2017, 10:42

Yep. Noted that too.
User avatar
eugeneloza
 
Posts: 490
Joined: 22 Aug 2014, 12:15
Location: Ukraine

Re: Help train Mozilla's open source voice recognition

Postby Julius » 30 Nov 2017, 16:03

“You never change things by fighting the existing reality. To change something, build a new model that makes the existing model obsolete” - Buckminster Fuller
User avatar
Julius
Community Moderator
 
Posts: 2142
Joined: 06 Dec 2009, 14:02

Re: Help train Mozilla's open source voice recognition

Postby Lyberta » 01 Dec 2017, 10:17

Heh, I would like the ability to command bots in a video game using speech.
Some crazy person on the Internet.
User avatar
Lyberta
 
Posts: 378
Joined: 19 Jun 2013, 10:45

Re: Help train Mozilla's open source voice recognition

Postby Julius » 01 Jul 2018, 20:48

Now also with some other languages and some interface changes.
“You never change things by fighting the existing reality. To change something, build a new model that makes the existing model obsolete” - Buckminster Fuller
User avatar
Julius
Community Moderator
 
Posts: 2142
Joined: 06 Dec 2009, 14:02

Re: Help train Mozilla's open source voice recognition

Postby mdtrooper » 04 Jul 2018, 08:14

I am thinking about the disable people. Some years ago, my couple was in bed for a month more or less (a health problem in the back) and I made (as DIY) a PC for this situation. We has a PC for to see films in the dinning room with a wireless keyboard (with mouse) and projector. Well I put this PC in the bedroom and the projects targeted to top wall (it's say in spanish? For the wall that hangs the lamp) and she could do her things (chat in social networks, study, see videos ... ).
User avatar
mdtrooper
 
Posts: 105
Joined: 26 Jul 2012, 13:24

Re: Help train Mozilla's open source voice recognition

Postby SecureUvula » 04 Jul 2018, 18:57

Top wall = ceiling

https://en.wikipedia.org/wiki/File:Ceil ... Agadir.jpg

"Couple" in English usually refers to two people in a romantic relationship.
"My partner" would be more common, or "my wife" if you're married and she is a woman. "Girlfriend" if you're not married yet.

Hope that helps! English is the JavaScript of human languages - Popular but insane
Itch: https://activated-onion.itch.io/

"Not only does he do it for free, he doesn't do it at all."
User avatar
SecureUvula
 
Posts: 32
Joined: 22 May 2018, 03:26

Re: Help train Mozilla's open source voice recognition

Postby Magellan » 06 Jul 2018, 19:52

SecureUvula {l Wrote}:English is the JavaScript of human languages - Popular but insane


That's great! I am going to say this all the time now :D
I make Let's Play videos of FOSS games. You can find them on DTube and VidLii. I have also made a few small Free Software games, available on my GitHub page.
User avatar
Magellan
 
Posts: 32
Joined: 24 Mar 2017, 02:25
Location: USA

Re: Help train Mozilla's open source voice recognition

Postby Soucy » 10 Aug 2018, 16:53

I'm impressed with the progress they've made. More power to the folks at Mozilla!
Soucy
 
Posts: 1
Joined: 03 Aug 2018, 10:52

Who is online

Users browsing this forum: No registered users and 1 guest