So this week, I only worked two days (Thursday, Friday). Last week I worked an extra day (Saturday), so I’ll make up 2 days I missed this week in the 11th week, so expect to see my blog post in the 11th week.

Web Speech API

So I only had two days to work with this. I ended last week mostly getting it set up with WebRTC + Web Speech API. Came back yesterday (Thursday, June 11) to resume my working schedule, and continue to troubleshoot the issues I had with getting web speech API to work properly with WebRTC. I also spent some time studying my co-intern partner, Emelia Beldon, on her successful work with Microsoft Azure ASR. It works successfully in a WebRTC environment. So there are some functions that she and another senior researcher, Norman, worked on. I took some time to read and understand those functions and try to implement it in a similar way with Web Speech API. Unfortunately, it is not as easy as it looks. Microsoft Azure has a SDK that can be implemented straight into the source code. Web Speech API on the other hand is a default implementation that a browser recognizes. Google Chrome recognizes this by default, and another browsers are in the process of supporting it. Therefore, there is no SDK, so I have to work with the code somewhat differently from what is being built for WebRTC + MS Azure implementation. That’s pretty much what I was doing the past 2 days. To remind you, this weekly blog post is a short one due to my short work week. More to come next week, farewell!