Re: improving accuracy of Speech recognition

This mailing list is for the discussion of the Web Speech API specification.
The Web Speech API is a JavaScript API that has been implemented in various
browsers.

Your question appears to refer to a different API, and has already been
answered.  Please see:

https://lists.w3.org/Archives/Public/public-speech-api/2014Dec/0001.html
https://lists.w3.org/Archives/Public/public-speech-api/2014Dec/0003.html

On Mon, Jun 15, 2015 at 6:17 AM, Deven <deven@binaryveda.com> wrote:

> Hi,
>
> I have been trying to use Google's Web Speech Api for speech to text
> recognition. This is the current flow of things. I am using python for this
> purpose.
>
> - Take input from microphone
> - Segment the audio using Voice Activity Detection.
> - Send the segment to Google's web speech API (on a thread)
> - print the response of the API
>
> Using this i could only get upto 60-65% conversion accuracy. Is there
> anyway to improve this? Would doing a pre-processing on the audio
> (noise-removal, filtering etc) help?
>
> --
> regards,
> D.Patel
>
>
>
>