[OLPC-GSoC] New Idea: Speech Recognition API

[Samuel Klein]

Hi Haoyu, something like simple phrase recognition, or disctimination
between pronunciation of a small list of options, can get you quite far in
terms of verbal interfaces or flashcard/recitation practice.

I think perhaps some of the people interested in mentoring text to speech
might also be interested in this.

SJ

On Tue, Apr 1, 2008 at 12:44 PM, Haoyu Bai <divinekid at gmail.com> wrote:

> Hello,
>
> I am a student from China. I have experience with speech recognition
> algorithms and practice. I am thinking add speech recognition ability to
> OLPC.
>
> I have read this wiki page: http://wiki.laptop.org/go/Speech_recognition
>
> In my opinion, since XO don't have a fast cpu, normal speech recognition
> algorithm and engine like Sphinx may not suitable. PocketSphinx may be
> faster, but its' training progress still slow.
>
> If we aim to some simple application like voice command, algorithm like
> DTW can be used, it is faster, but only can do simple phase recognition.
>
> I have no clear idea right now. I want to know is there a mentor
> interested in it? So we can discuss it deeply.
>
> Thank you!
>
>
> Best regards,
>
> Haoyu Bai
> 4/2/2008
> _______________________________________________
> Gsoc mailing list
> Gsoc at lists.laptop.org
> http://lists.laptop.org/listinfo/gsoc
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://lists.laptop.org/pipermail/gsoc/attachments/20080402/7324b7fd/attachment.htm