Live data from Hacker News

Watson now brings cognitive speech capabilities to developers

developer.ibm.com

41–42 of 42 posts

Re: Watson now brings cognitive speech capabilities to developers

#41

Post by aroopPandya » Thu, Feb 12, 2015, 4:18 PM UTC

kovacs wrote: post #39

aroopPandya wrote: post #37

Earlier quoted context omitted.

Hi..are you free on Thursday morning I can meet up at your choice of place and work through with you..

I am free. Email me at kovacs@gmail.com I did get things working and am working on a ruby gem that I'm hoping to be able to release for general consumption but in the mean time for folks using ruby here's a snippet that will get the simple case working once you've setup a bluemix app and bound the speech to text service to it: https://gist.github.com/kovacs/72ad554a773a62818d46

PM sent let..can meet during lunch today and be happy to meeet

Re: Watson now brings cognitive speech capabilities to developers

#42

Post by oomkiller » Wed, Feb 18, 2015, 5:35 PM UTC

vaibhava72 wrote: post #38

oomkiller wrote: post #18

The ability to create your own models is very important to use this, as your existing ones do a bad job of processing my normal speech. To test I just tried reading a few simple phrases and the error rate is pretty high. The Web Speech API did a great job with the same phrases https://www.google.com/intl/en/chrome/demos/speech.html

Just to rule out a known issue with some laptop built-in microphones (e.g. https://developer.ibm.com/answers/questions/174176/speech-to... ) - could you let us know if you tried with an external close-talking microphone, and if that mattered at all?

It seemed a bit better with my bose headset, but still was quite lacking.

Post reply on HN