Scribd
Upload
38 views16 pages

BDHXB

Speech recognition technology allows machines to understand human speech and convert it into text or commands. It draws from many fields including physiology, psychology, linguistics, computer science, and signal processing. The goal is natural language communication between humans and machines. The paper describes the development of speech recognition technology, its principles, methods, and systems. It analyzes challenges in speech recognition.

Uploaded by

raj chow
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
38 views16 pages

BDHXB

Speech recognition technology allows machines to understand human speech and convert it into text or commands. It draws from many fields including physiology, psychology, linguistics, computer science, and signal processing. The goal is natural language communication between humans and machines. The paper describes the development of speech recognition technology, its principles, methods, and systems. It analyzes challenges in speech recognition.

Uploaded by

raj chow
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 16

As a cross-disciplinary, speech recognition is based on the voice as the

research object. Speech recognition allows the machine to turn the speech
signal into text or commands through the process of identification and
understanding, and also makes the function of natural voice communication.
Speech recognition involves many fields of physiology, psychology, linguistics,
computer science and signal processing, and is even related to the person's
body language, and its ultimate goal is to achieve natural language
communication between man and machine. The speech recognition technology
is gradually becoming the key technology of the IT man-machine interface. The
paper describes the development of speech recognition technology and its
basic principles, methods, reviewed the classification of speech recognition
systems and voice recognition technology, analyzed the problems faced by the
speech recognition.
Introducing Our Roles
SpeakNote Till Now
Team Members Current
Introduction Progress

Project Guide Advantages Of


Introduction Our Website

Technologies and Our Website


Languages Used Subscriptions
Development Future Plans
Process And Ideas

Conclusion
Automated Notes Maker From Audio Recordings
Transcribing lectures or speeches
Accessibility for the hearing impaired
Dictation
Improved productivity
Language learning
Translation
Our Team ( Group-09 )
We as an innovative and creative-
thinking group of four developers
and coders have discussed and
Name of College Roll
decided to make our project on this
Member Number topic, that is, “Automated Notes
Maker from Audio Recordings.”
Rajdeep 037
Chowdhury
(EEE 6th
semester)
Rounak Dey 012
(EEE 6th
semester)
Prabhat Jha 038
(EEE 6th
semester)
Sakshi Jha 011
(EEE 6th
semester)
Assistant Professor at Academy of Technology
Our project guide, Prof. Abhijit Patra, shed light upon us
about the nature and path of learning for the project and
the execution of the concepts.
He helped us in getting the right materials from the internet
to study and do our research on to make this project possible.
He gave us the correct motivation for this project. He
reviewed our process and the code and the overall look of
the after periodic intervals of time and told us our mistakes
and areas we can improve on.
The technologies,
languages and third party GitHub or
websites used in building
HTML5
Vercel VS Code
and deploying this The website’s “skeleton” We are suing the standard
is made with HTML5. Code editor for writing all the
website are given as
code and managing the files.
follows: CSS3
CSS3 HTML5 GitHub
The website’s styling ,i.e., We will deploy the project files
UI/UX is done with CSS3. on GitHub platform in a separate
repository.

ReactJs Node.js
We are planning to further build the JS API We are coding the functionalities
project and integrate ReactJs and of the website in JavaScript through
divide the whole page into components. Node.js framework.
VS Code
Speech Recognition API Editor Hosting Website
We have used Web Speech Hosting website to get our
API's Speech Recognition for personalized domain name like
Converting speech to text. Hostinger (www.hostinger.in),
or some other provider.
The detailed development process using HTML5, CSS3,
JavaScript, and API is given as follows

Create a new JavaScript file and add the necessary code to


handle the transcription process. Add event listeners to the Link the JavaScript file
SpeechRecognition object to handle the various stages of the to the HTML file using
recognition process, such as onstart, onresult, onend, and the <script> tag.
onerror. <script src="transcription.js"></script>

Create a new CSS file and add the


necessary styles to format the Test your transcription
webpage. website by opening the
HTML file in a web
browser.
Keep in mind that this is
Create a new HTML file and add the just a basic example and
necessary HTML tags to set up the you may need to
basic structure of your webpage. customize the code to fit
your specific needs. You
<!DOCTYPE html> may also need to handle
<html>
issues of privacy and
<head>
<title>SpeakNote</title> security when working
</head> with user data, such as
<body> speech input.
<h1>Transcription Website</h1>
<textarea id="transcription"></textarea>
<button id="start">Start Transcription</button>
<script src="transcription.js"></script>
</body>
</html>
The project work is divided among the four members in our team

• We did the coding of the main logic and all functionalities of the website
by implementing them in JavaScript and Reactjs. We did the adding of all
the speech to text functionalities of the website by using the API.
• We took care of all the modules and the documentation related to the
project that need to be studied and used in our project concept.
• We did the of designing (UI/UX) and styling of the website on Figma and
developing the CSS part of the coding.
Current Progress

Present progress and reviewable links


Presently, our website can detect any sentence of any Here is a google drive video link which is a screen recording of
selected language and covert it into text simultaneously and the website functioning smoothly and efficiently and doing the
then the entire text is downloadable in .txt format. required job without hesitation:
We have much improvement and additional features left to https://drive.google.com/file/d/1bfM1FxBD1y47TDZI9EsYFzrj
be added to the website and we as a team are working on it dhnDhqgT/view?usp=share_link
taking guidance and help from our project guide. Here is the link of the GitHub repository of the uploaded project:
https://github.com/deepbeatz/SpeakNote
Accessibility
Automation
This website can make technology more
This website in future will automate
accessible to people with disabilities like
manual transcription tasks, reducing the
hearing impairment, dyslexia, or speech
cost and time involved in hiring
disorders.
transcription professionals or using
Productivity traditional transcription software.
By utilizing the speed and accuracy of Innovation
API-powered speech recognition With the rise of voice-activated devices
technology, this website can save time like smart speakers and assistants,
for users who need to transcribe. speech-to-text technology will continue
to evolve and improve.
Multilingualism and diversity
This website that can recognize and Transcribing lectures or speeches
transcribe various languages. It can also Students can use speech to text websites
celebrate diverse accents and dialects by to transcribe recorded lectures or
accurately transcribing them. speeches, making it easier to take notes
and review important information.
We plan to charge money for our services in the future
For now our services are free until we take our website to its planned potential

Pro Plan
Regular Plan Advanced Plan

199
For 1 month subscription
499
for 3 months subscription
999
for 6 months subscription

Record & Transcribe Record & Transcribe Record & Transcribe


Note-taking
Edit and Highlight
v
Note-taking Note-taking
Edit and Highlight
Edit and Highlight
Share Share Share
Import and Export Import and Export Import and Export
Customization Customization Customization
Integrations Integrations Integrations
Collaboration Collaboration Collaboration

More Detail More Detail


More Detail
We have done sufficient discussion and group work to increase the project
reliability, user friendliness and cost effectiveness of our website. This is still
and ongoing process and we aim to take the website to its true potential such
that any person from any part of the world can use this website without
hesitation to get speech-to-text results with maximum accuracy and minimum
time and have a good experience surfing the website and also satisfied with its
user friendliness and designing/styling.

We have planned the following for the near future:


• Integrating ReactJS and dividing the whole website (aiming to be a multi-paged
website) into components and improving the UI/UX of the website.
• Searchable transcripts: The transcripts that will be generated by SpeakNote will
be searchable, which will make it easy to find specific sections of the audio or
video.
• Note-taking: SpeakNote will allow users to take notes while listening to audio or
watching video, and these notes can be synced with the transcript.
• Multi-device syncing: Users will be able to access their transcripts and notes on
multiple devices, including desktop computers, smartphones, and tablets.
• Collaboration: SpeakNote will allow users to share their transcripts and notes with
others, making it easy to collaborate on projects or share information.
• Integration: SpeakNote will be able to integrate with other tools, such as Zoom,
Dropbox, and Google Drive, which will make it easy to use in conjunction with
other tools.
• Voice commands: SpeakNote will offer voice commands for navigation and editing,
which can help speed up the transcription and note-taking process.
An audio to text converter website can be a valuable tool for
anyone who needs to transcribe spoken words into written
text quickly and accurately. Our website SpeakNow can
save time and increase productivity for professionals such as
journalists, students, and researchers who frequently work
with audio recordings. With advancements in machine
learning and natural language processing, audio to text
converter websites are becoming increasingly accurate and
reliable, and they can even recognize and transcribe multiple
speakers. While there may be some errors in the
transcription process, users can typically edit the text to
correct any mistakes. Overall, our audio to text converter
website can be a powerful tool for anyone who needs to
convert audio recordings into written text efficiently and
accurately which is fulfilled by our designed website
'SpeakNow'.
The websites used for taking help with the making of this ppt and
with the making of the entire project were as follows:

1. www.geeksforgeeks.org
2. www.wikipedia.org
3. www.w3schools.com

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy