Scalability4All Voice Enabled Chatbot

Implementing a voice enabled chatbot which converses with a user via their voice in natural language.
The chatbot can be configured through domain-specific.

Responsive

Connect fast and response to user query as soon as possible.

Emotional-Aware

Find the chat intent before answering the query.

Interactive

Play vital role in building chat with inactive people and dive them into active customers.

Data Driven

Client can configure the domains and corresponding data to give personalized response to customers.

Open Source

Clients have chatbot code available so they can tune the code according to requirements.

Clean Design

We will put multiple configurable methods for chatbot to setup service for our clients.

About Me

We are a group of oriented and self-driven technologists who is passionate about solving challenging problems. We are trying to put open source solutions for scalable problems in machine learning. This will help our clients and supporters to use the code and our service to use our code which will help them to focus on their core problem.

Concept

Weather Information

Hey, what is the weather today?

Will it rain today?

Location Information

I want to know if there are any shopping stores near me

Inventory Information

Can you tell me availability of item in Store X?

If we have topics like the weather, location information, inventory information etc the application should be able to converse in that particular topic.

I want to know if there are any shopping stores near me.

These are the nearest stores:- A, B, C. Where do you wanna go?

I want to go to the most popular one among them

All right, showing you directions to C.

So, mainly the chatbot should formulate appropriate responses to incoming questions and carry on the conversation. Keeping in mind, the conversation would be in natural language and the user is returned sufficient information.

Process

Step 1: Given a speech through Microphone, Store it and Convert it using SpeechRecognition and PyAudio.
Step 2: Topic Modelling: Get Entity and Intent of chat using model with a corpora. To get the trained model, we will use the classifier to categorize it to weather, location and inventory. After that using RASA-NLU with Spacy library, we will get the entities.
Step 3: After Finding Intent and Entity, we will set model in following method: Intent = Weather: Based on entity specified, We will use weather API to get data about location. Intent = Location: Following Conversation flow: Get Stores located or Any Nearby Stores Choose Store Inventory Details about Store
Step 4: Use cache mechanism to give result about recently used query.

Installation

Clone the repo

Clone the voice-enabled-chatbot repo locally.

View Project

Install Dependencies

We need PyAudio, a cross-platform audio I/O library. Install other requirements given in below link.

Requirements

Skills

Good Understanding of Machine Learning, specifically NLP.
Experience with HTML, CSS, and JavaScript
Experience with GIT and the command line
Knowledge of Intent, Entity and classification is preferred.
Interest in implementing unit, integration, and acceptance tests
AngularJs
Interest in accessibility in web development and performance optimisation
Interest in data science and learning new techniques.
Passion for the project and a desire to build and learn