<br>Hello, <br><br><div class="gmail_quote">On Mon, Jun 23, 2008 at 1:05 AM, <<a href="mailto:prishelec@gmail.com">prishelec@gmail.com</a>> wrote:<br><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
Will it be possible to use it with voice dialing?<br>
You said vocabulary is 5-10. Will it be enough?<br>
It would be cool if I would have a possibility to say: "Message to<br>
Jane" to open sms dialog or "Call to Jane" to call, presuming Jane is<br>
a hot chick ;-)<br>
Is it possible?<br>
<div><div></div><div class="Wj3C7c"></div></div></blockquote><div><br>yes, it is of course possible.<br>
<br>But it requires the speech recognition for connected words which needs
the level building algorithms and proper noise handling along with
learning grammar for machine. This project has a great scope and can be
extended to any limit. However in this small duration for GSoC Project,
I dont think that it will be possible to incorporate these advanced
features in it. The initial aim will be to provide an API in which user
can store his/her own words individually and connect any particular
activity with that word. Upon detection of that word, the API
corresponding to that activity for that word will be called. I have
included these points in my Design Document and the scope of advanced
models using speech recognition. I think once the individual word
recognition application is built, the advanced features can be added
using this application and newer one. <br> </div><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;"><div><div class="Wj3C7c"><br>
On 6/22/08, saurabh gupta <<a href="mailto:saurabhgupta1403@gmail.com">saurabhgupta1403@gmail.com</a>> wrote:<br>
> Hello everyone,<br>
><br>
> This is the status update of the GSoC project, Speech Recognition facility<br>
> in Openmoko. This week, much of the time was devoted in writing codes and<br>
> optimizing the existing one. I have written many subroutines like forward<br>
> backward procedure, LPC and cepstral analysis of speech signals in frames,<br>
> viterbi algorithm and training algorithm using K-means segmental method. All<br>
> the source codes have been successfully compiled using GNU C compiler.<br>
> There are various optimizations done in the coding to make it suitable<br>
> for working on the ARM 16/32-bit processor running at 266 or 400 MHz<br>
> maximum. The whole code is written using fixed point arithmetic. I used<br>
> some external libraries for some subroutines and converted them in fixed<br>
> point arithmetic. The other optimization was done by choosing K-means<br>
> segmental procedure for training the HMM models rather than Baum Welch<br>
> algorithm which requires more processing since it accounts for all the<br>
> possible hidden states for a given sequence. On the other hand K-means<br>
> segmental method uses viterbi algorithm to find the best state sequence and<br>
> then iterates for re-estimation and training the HMM model. K-means<br>
> segmental method has been proved to show good results and fast processing<br>
> than Baum-Welch. The other optimization is regarding the probability density<br>
> function. As this project aims for a small vocabulary (around 5 or 10) for<br>
> recognition, vector quantization will be used instead of continuous<br>
> observation sequence. Vector quantization procedure is faster and yields<br>
> good result for applications in small embedded devices. The vector<br>
> quantization source code is about to finish. Soon after that, the actual<br>
> testing of speech recognition code will be done on the speech samples<br>
> collected.<br>
> I have uploaded all Documents (Design Document version-0.2) and<br>
> source codes on the svn repository of Openmoko (<br>
> <a href="https://svn.projects.openmoko.org/svnroot/speech/" target="_blank">https://svn.projects.openmoko.org/svnroot/speech/</a>). Any comments and<br>
> suggestions will be highly appreciated.<br>
><br>
> <a href="http://saurabh1403.wordpress.com/" target="_blank">http://saurabh1403.wordpress.com/</a><br>
><br>
> Regards....<br>
> --<br>
> Saurabh Gupta<br>
> Electronics and Communication Engg.<br>
> NSIT,New Delhi<br>
><br>
<br>
</div></div>_______________________________________________<br>
Openmoko community mailing list<br>
<a href="mailto:community@lists.openmoko.org">community@lists.openmoko.org</a><br>
<a href="http://lists.openmoko.org/mailman/listinfo/community" target="_blank">http://lists.openmoko.org/mailman/listinfo/community</a><br>
</blockquote></div><br><br clear="all"><br>-- <br>Saurabh Gupta<br>Electronics and Communication Engg.<br>NSIT,New Delhi<br><br>