[Eeglablist] ASR question

Makoto Miyakoshi mmiyakoshi at ucsd.edu
Tue Oct 6 10:42:03 PDT 2015


Dear Jianwei,

> 20-30%

This is normal, so  don't worry.
Christian (the author) told me that the minimum is 7-8%.

Makoto

On Tue, Sep 22, 2015 at 9:39 PM, Amy <amycao723 at gmail.com> wrote:

> Hi All,
>
> I have one question regarding ASR:
>
> When I use ASR to process the dataset, it always keep only 20%-30% of the
> original data(120 seconds), the resting 70-80% of the original data is
> corrected by ASR. So I am wondering whether the 20-30% for keeping is too
> small, do I need to increase the parameter of SD in ASR? I usually keep the
> SD parameters as 4 and 5 as default in ASR.
>
> Thank you,
>
> Jianwei
>
>
> Sent from my iPhone
> _______________________________________________
> Eeglablist page: http://sccn.ucsd.edu/eeglab/eeglabmail.html
> To unsubscribe, send an empty email to
> eeglablist-unsubscribe at sccn.ucsd.edu
> For digest mode, send an email with the subject "set digest mime" to
> eeglablist-request at sccn.ucsd.edu
>



-- 
Makoto Miyakoshi
Swartz Center for Computational Neuroscience
Institute for Neural Computation, University of California San Diego
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://sccn.ucsd.edu/pipermail/eeglablist/attachments/20151006/9bb9612f/attachment.html>


More information about the eeglablist mailing list