Hi,

I have been thinking about a speech-to-text tool on N-900. One that can transcribe the speech in an almost readable form. Though there is a selfish motive for it which I will be explaining here, but in general, it might prove to be useful for most of the people. Two of the strong reasons to have a working speech-to-text software are:

1. In my case (I am a student), it would help me in transcribing all that happens in a particular session of the lecture, easing my workload of taking notes. In most cases, it would help in assignments and stuffs like that.

2. The same issue of transcribing may be applied with regard to certain meetings/discussions etc., this would ease the task of documentation and things like those.

The major question that people first see is its accuracy. IMO the google's app in iPhone (for voice search) or in android (various apps) is highly effective in finding out the correct words in most cases. Though this is internet dependent, but still, it does the job in an efficient manner. But I am not completely sure if I would be able to port that here (should be doable).

Plus with google announcing their research on Voice-to-Voice translation, my hopes of a good system has certainly gone up.

We can also have native systems to do the job like CMU's PocketSphinx which are optimized for ARM processors. But then, the accuracy of these systems are debatable. There were also a couple of discussions on the OLPC wiki about the speech-to-text warez, but they are still in their incipient stages.

The question now is, how useful will this application be in your view? Are there any better ways to do this? Any significant approaches? Or is there any other project which is following the same route/path, I would certainly like to join and would like to contribute my bit.

---
Kakashi (Pranav)

I'd love to see it, do you think it will ever work at least decently?

No software I ever got my paws on ever did a decent job of getting even a phrase down. Even with hours of training. Must be the accent.

IMO, if somehow, if we could get the suggestions from Google (huge data) it should be doable. Still need to do a bit of search on that, but the Gaudi (http://labs.google.com/gaudi) gives me a lot of hope.

That is the reason I am a bit hesitant on native applications.

Show an existing open source project that does this.

cmu sphinx perhaps?

ANY OPEN-SOURCE SPEECH TO TEXT APP WILL NOT BE SPECIFIC TO N900.

GET IT?

Thanks a lot for replying!

I am no expert on this. There is PocketSphinx which is mostly made for ARM processor.
Or you also have services like Voice on the Go (http://www.voiceonthego.com) or Yap (http://www.yapme.com/) which can do the Job. Ofcourse there is the Giant Google (I mean it has to be a hack to use the api).

I am not emphasizing right now on native software(s).

You get the point?

I don't think we are there yet for continuous large vocabulary recognition, but using voice recognition for small vocabulary recognition can work really well, even on mobiles.

I don't think you will see any apps for n900 that will take down your extemporaneous dictation but there may be something you can use to give voice commands

moved... as you are new here, it is not new to read sticky topics in forums. also there is already a brainstorm! read the links in my sig before you start posting in brainstorm again please

As far as I know, Linux doesn't have a decent text-to-speech program. I would appreciate it if any disagreement with that statement would begin, "I use ____ to dictate chapters"... etc.

I have read many chapters and they were translated into text, but only using Windows software such as Dragon Naturallyspeaking.

Of course, short commands are a different story.

I'm pretty sure Google suggestions are going to get me a divorce. :)

As long as it isn't cloud-based...