Thursday, September 28, 2017

How to : Your VOICE Based AI

#SpeechRecognition #VoiceBasedAI #DeepLearning #SpeechToText #Abzooba Created a simple Voice based AI Assistant using speech recognition library in python. It does the following : 1) Understands voice 2) Can convert speech to text ( My starting point , as wanted an Assistant who can help me write my stories )

3) Perform simple actions ,Like ?

3A) You ask for the current time and get's it instantly. 3B) Understands the intent or context in the speech and can perform specific action e.g. When I ask Rudra ( Have named my AI after Lord Shiva ) to find the location of a place , it automatically opens Google Map with the particular location , or when I ask to find a similar kind of shirt by providing the picture of a blue shirt , it scans the image and then find similar looking shirt in #Amazon or #Myntra.

Interesting, isn't it?

Pray to Lord Rudra and get started !

Let's look into how I did it.

Some Important Stuff FIRST -

For Speech Recognition, you need Speech Recognition library.

Do a pip install and get it installed.

pyaudio will also be required.

I am using Keras ( which using tensorflow backend) here for further processing .

Google has a great Speech Recognition API. This API converts spoken text (microphone) into written text (Python strings), briefly Speech to Text.

text-to-speech (TTS) system converts normal language text into speech.

Let's Look into the WorkFlow :

Let's see how it works :

A)  I say what TIME is it ....

Good, let's move to more complex stuff !

B)  I say to find me a Location like let's say I ask - Where is Abzooba ?

Automatically opens up Chrome browser with Goggle Map location the particular address.

Great , now let's move to more Complex things .

C) I show an Image to Rudra - I have kept the image in a folder as for now but once you create a simple UI along with it you can just upload the image .

I ask Rudra to search for similar item in #Myntra

Rudra scans the image and then automatically opens up Myntra for the possible choices.