voice recognition

The voice recognition is the essential part of the smartphones like Siri, Alexa and Google. But the weak point of these voice recognition systems is that they come with the corresponding delay and you have to wait for Siri and others to respond to our query. There are chances of your query to be correctly interpreted or horribly mangled.

Advertisement

Now Google‘s latest voice recognition system is available for you without any delay. The mangling is still an option for you. Your voice, or some data derived from it, has to go through from your phone to the servers of whoever operates the service, where it is analyzed and your required query is answered within some time, which cause the delay. This can take up to milliseconds to multiple entire seconds, and I know it is not easy to wait.

So, what if voice recognition comes on the device itself? Everybody including customers and as well as companies will love it. But turning voice into text can take some of computing work power. Understanding what someone is saying word by word requires a whole lot of information about language and intention.

Google to create a model which is small and efficient enough to fit on a phone, it is probably 80 megabytes. All you have to do is just say what your query is all about, it will be transcribed and write it down for you. It hears all your voice and you don’t want to think afterward that you have to say there or their, it will figure out for you.

read also: Indian police arrested ten students for playing PUBG game

Well, the real stress test is that it only works with some conditions like it only works in Gboard, Google’s keyboard app, and it only works on Pixels, and it only works in American English.

Google writes :

“Given the trends in the industry, with the convergence of specialized hardware and algorithmic improvements, we are hopeful that the techniques presented here can soon be adopted in more languages and across broader domains of application,”

Well, the real stress test is that it only works with some conditions like it only works in Gboard, Google’s keyboard app, and it only works on Pixels, and it only works in American English.

Also, it’s a very nice development of making speech recognition more responsive, and to make it work offline.

 

Advertisement