lOMoARcPSD|38824818

AI voice assistant PPT - Project ppt

Artificial Intelligence (SRM Institute of Science and Technology)

Scan to open on Studocu

Studocu is not sponsored or endorsed by any college or university

Downloaded by xboy xman ([email protected])
 lOMoARcPSD|38824818

VOICE ASSISTANT

Downloaded by xboy xman ([email protected])

 lOMoARcPSD|38824818

Prasoon Priya Gautam

- RA2011033010180
Aniket Wakodikar
- RA2011033010183

Contribution:
RA2011033010180-Objectives, Pros, and
Cons, Proposed Methodology- speech
recognition module
RA2011033010183-Introduction, Literature
Survey, Proposed Methodology- pattern
recognition
Both the members-Architecture Diagram,
Modules needed in voice assistant, Proposed
Methodology-User Interface
2
Downloaded by xboy xman ([email protected])
 lOMoARcPSD|38824818

PROBLEM STATEMENT

The client wanted to build a voice assistant application that would

enable children to interact with the tablet through voice. The
application should be triggered by a voice command /keyword (like
Ok Google or Hey Siri). The application should work online and offline
and should provide answers to a predefined library of questions. If
the questions asked are not in the library, the application should
search online on google and provide an answer. The library of
questions will be updated regularly and pushed through software
updates.

3
Downloaded by xboy xman ([email protected])
 lOMoARcPSD|38824818

A LITERATURE SURVEY ON VOICE ASSISTANCE

MONTH AND YEAR OF PUBLICATION:APRIL2022

4
Downloaded by xboy xman ([email protected])
 lOMoARcPSD|38824818

OBJECTIVES
The main objectives of voice assistants in points:
. Provide information
2. Perform tasks
3. Control devices
4. Personalize interactions
5. Understand natural language
6. Enable multimodal interactions
The overall objective is to make technology more
convenient, efficient, and intuitive for users to interact
with using spoken language.

5
Downloaded by xboy xman ([email protected])
 lOMoARcPSD|38824818

PROS AND CONS OF VOICE ASSISTANTS

PROS: CONS:

1. Convenience 1. Privacy concerns

2. Efficiency 2. Accuracy issues

3. Accessibility 3. Dependence

4. Personalization 4. Cost

5. Integration 5. Technical issues

6
Downloaded by xboy xman ([email protected])
 lOMoARcPSD|38824818

PROPOSED METHODOLOGY
• User Interface: User interface module will be used by both Professor and students. User interface module will
help to interact with Students and Professors vice versa. This module will contain all designing of web
applications containing all views of activities like schedule exam, Complete training etc. In this module we are
going to use asp.net MVC with HTML and CSS.

• Speech Recognition Module: As the name suggests this module will help in recognizing the voice of the user.
We will use windows speech recognition library to recognize speech. Speech recognition libraries will recognize
commands given by use and will convert them into text. As per voice we will also recommend various commands

• Pattern recognition: It is the process of recognizing patterns by using machine learning algorithms. Pattern
recognition can be defined as the classification of data based on knowledge already gained or on statistical
information extracted from patterns and/or their representation. One of the important aspects of the pattern
recognition is its application potential.

7
Downloaded by xboy xman ([email protected])
 lOMoARcPSD|38824818

ARCHITECTURE DIAGRAM

Use Case Diagram Activity diagram

8
Downloaded by xboy xman ([email protected])
 lOMoARcPSD|38824818

Modules needed in Voice Assistant

1-SpeechRecognition: This module is used for recognizing speech from the audio input.

2-PyAudio: This module provides a way to play and record audio using Python.
3-pyttsx3: This module is used for text-to-speech conversion.
4=Pyttsx: Similar to pyttsx3, it can also be used for text-to-speech conversion.
5=WolframAlpha: This module is used for retrieving information from the Wolfram Alpha computational knowledge
engine.
6-Wikipedia-API: This module provides an easy way to access Wikipedia content and search for articles.
7-OpenAI API: This module provides an easy way to access Open Ai's powerful AI models for natural language
processing and understanding.
8-NLTK: This module provides a wide range of natural language processing tools such as tokenization, stemming,
lemmatization, and more.
9-NumPy: This module is useful for mathematical computations and handling arrays.
10-Pandas: This module is useful for data manipulation and analysis.
11-Requests: This module is used for making HTTP requests to retrieve data from APIs.
12-JSON: This module is used for working with JSON data.

Note that the modules used in a voice assistant application can vary depending on the specific requirements
and functionalities of the application.

9
Downloaded by xboy xman ([email protected])
 lOMoARcPSD|38824818

FEATURES

• Support for offline and streaming use cases

• A streaming mode that returns intermediate transcripts with low
latency
• GPU-accelerated feature extraction
• Multiple (and growing) acoustic model architecture options
• Beam search decoder based on n-gram language models
• Voice activity detection algorithms Automatic punctuation
• Ability to return top-N transcripts from beam decoder
• Word-level timestamps
• Inverse Text Normalization

10
Downloaded by xboy xman ([email protected])
 lOMoARcPSD|38824818

SOURCE CODE

11
Downloaded by xboy xman ([email protected])
 lOMoARcPSD|38824818

GITHUB REPOSITORY
CODE

12
Downloaded by xboy xman ([email protected])
 lOMoARcPSD|38824818

GITHUB REPOSITORY

GITHUB LINK https://github.com/

humhongekaamyaab/Voice-
Assistant---Chitti

NAME : PRASOON PRIYA

GAUTAM

REG. NO : RA2011033010180

Downloaded by xboy xman ([email protected])

 lOMoARcPSD|38824818

GITHUB REPOSITORY

GITHUB LINK
https://github.com/
ANIKETwakodikar/
AI_voice_assistant

NAME : ANIKET WAKODIKAR

REG. NO : RA2011033010183

Downloaded by xboy xman ([email protected])

 lOMoARcPSD|38824818

Analysis
LINEAR REGRESSION CONCEPT
This algorithm is a method of finding a linear relationship
between a dependent variable and an independent
variable by minimizing the distance. This is a supervised
algorithm. Here, we use a machine learning supervised
algorithmic approach to categorize individual categories.
Using this algorithm, we created a voice assistant model
that allows users to predict relationships between
dependent and independent entities.

D=p+qI p= (D)(I2 )-(I)(ID)n(I2 ) - (I)2 (D)(I2 ) - (I)(ID)n(I2 ) -

(I)2 q= n(ID) - (I)(D)n(I2 ) - (I)2
I is the independent variable
D is the dependent variable
p is intercept and
q is slope of line here

15
Downloaded by xboy xman ([email protected])
 lOMoARcPSD|38824818

DATA TRAFFIC

16
Downloaded by xboy xman ([email protected])
 lOMoARcPSD|38824818

RESULT

A virtual assistant is a software program that can understand commands and carry out tasks assigned by the
user, making it a time-saving tool. By utilizing natural language processing (NLP), a virtual assistant can
interpret and match user voice or text inputs with actionable commands. This technology enables users to
control their devices, such as a laptop or PC, through voice commands, making it a quick and efficient
process. We have developed a virtual assistant using Python, Machine Learning, and AI with the goal of
assisting users with their tasks through voice commands. This process involves two phases: first, capturing
the user's audio input and converting it to an English phrase using speech recognition.

Downloaded by xboy xman ([email protected])

 lOMoARcPSD|38824818

OUTCOME

During this research, we have built a voice-activated assistant that can do any action in response to
orders supplied by the user without mistake. More functions have been introduced, such as
listening exclusively to the users' speech and not being triggered by background noise. This project
is easier to grasp and more adaptable because of its modular design. The program's functionality
won't be affected if we add new features. The VS Code Integrated Development Environment was
used to implement the Python code, which included installing all of the necessary packages (IDE).
This project made use of Python 3.x and data from Other environmental sounds were also used to
create other noise 18
Downloaded by xboy xman ([email protected])
 lOMoARcPSD|38824818

FUTURE ENHANCEMENT

Enhancement in the capacity of database or the data training sets can be done in this for more
situations or the acquaintances that can be faced by JARVIS. This would upgrade its effectiveness and
the wide range ability of producing responses. Further addition of more voices can also be done as an
additional feature. So these limitations can be broken with the increase in data training sets. The
interface of the system can be improved more or we can say can be optimized. From saying more
optimized it is meant that the interface can be more user friendly, comprehensive and easy to use for
more percentage of users. So the Jarvis would become more accessible and intractable .

19
Downloaded by xboy xman ([email protected])
 lOMoARcPSD|38824818

CONCLUSION

An AI Voice Assistant System uses speech recognition, gTTs and other AI techniques along with
Neural Networks and Natural Language Processing for a smart responsive system to the given
circumstances or conditions. It can reduce the workload of basic human activities or the daily
activities and can replace some human working posts like personal secretaries employed for
scheduling a person’s per day time table. Critically, the system is designed to interrelate with
other sub-systems smartly and comprehensively. The system will have the following phases:
Input phase in which data or query given in form of text or speech, Interpretetion of voice to
text, Processing and storing of data, producing output in the form of voice from the refined
text to Jarvis console. The information produced at each step can then be used to retreive
patterns and analyze them for later use. This could be the main basis for artificial intelligence
machines to learn and recognize patterns for people. So, based on a literature study and
analysis of persisting systems, the conclusion is derived that our provided system will not only
facilitate interaction with systems and modules but also keep users more organized.

20
Downloaded by xboy xman ([email protected])
 lOMoARcPSD|38824818

REFERENCES
• “Desktop Voice Assistant With Speech Recognition Intelligence (DVAbot)”, International Journal for Research in Engineering Application &
Management (IJREAM), Aditya Tyagi, Harshi Singhal, Mradul Jain (2020)

• ”Voice Assistant Application for a college”, International Journal of Recent Technology and Engineering (IJRTE) Deny Nancy, Sumithra Praveen,
Anushria Sai, M.Ganga, R.S. Abisree(2019).

• “Development of a Virtual Teaching Assistant System Applying Agile Methodology”, Texas A&M International University, Dr. Pablo Biswas,Dr.
Runchang Lin(2012).

8/06/20XX PITCH DECK 21

Downloaded by xboy xman ([email protected])
 lOMoARcPSD|38824818

THANK YOU

22
Downloaded by xboy xman ([email protected])