Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Added images #5

Open
wants to merge 11 commits into
base: master
Choose a base branch
from
+562 −560
Open

Added images #5

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
bce6ad2
change info
Jan 12, 2025
8c4e805
my own information updated
Jan 13, 2025
2ff2196
my own photo information updated
Jan 13, 2025
d160a6f
my own photo information updated
Jan 13, 2025
0d55f3a
Create Project_details
lipsaroutray Feb 15, 2025
fd5b084
Add files via upload
lipsaroutray Feb 15, 2025
724fbd9
Add files via upload
lipsaroutray Feb 15, 2025
04ece99
Added project images
lipsaroutray Feb 15, 2025
bfd8de2
I modified index.html
Feb 15, 2025
12f546d
I modified images folder
Feb 15, 2025
741fe41
Update phd projrct description changes
Feb 15, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Binary file added .DS_Store
View file
Open in desktop
Binary file not shown.
3 changes: 3 additions & 0 deletions .vscode/settings.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,3 @@
{
"liveServer.settings.port": 5501
}
Binary file added Lipsa_IIT_Guwahati_Résumé.pdf
View file
Open in desktop
Binary file not shown.
1 change: 1 addition & 0 deletions Project_details
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@

366 changes: 366 additions & 0 deletions Project_details.html
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,366 @@
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8" />
<meta name="viewport" content="width=device-width, initial-scale=1" />
<title>Projects - Lipsa Routray</title>
<style>
/* CSS styling for the project page */
body {
font-family: Arial, sans-serif;
line-height: 1.6;
margin: 0;
padding: 0;
background-color: #f4f4f4;
}
.container {
width: 90%;
max-width: 1000px;
margin: 20px auto;
padding: 20px;
background-color: #fff;
box-shadow: 0 0 10px rgba(0, 0, 0, 0.1);
}
.project {
margin-bottom: 40px;
border-bottom: 1px solid #ddd;
padding-bottom: 20px;
}
.project:last-child {
border: none;
}
.project-title {
font-size: 1.8em;
margin: 0 0 10px;
color: #333;
cursor: pointer;
transition: color 0.3s ease;
}
.project-title:hover {
color: #007BFF;
}
.project-image {
width: 100%;
max-height: 300px;
object-fit: cover;
margin-bottom: 15px;
}
.project-details {
color: #555;
}
.project-details h3 {
margin-bottom: 5px;
color: #333;
}
.project-details p,
.project-details ul {
margin: 0 0 15px;
color: #666;
}
.project-details ul {
list-style-type: disc;
padding-left: 20px;
}
</style>
</head>
<body>
<div class="container">
<!-- Project 1: Cockpit Design for EV Buses in India -->
<div class="project">
<h2 class="project-title">Cockpit Design for EV Buses in India</h2>
<img src="images/cockpit_bus.jpg" alt="Cockpit Design for EV Buses in India" class="project-image" />
<div class="project-details">
<h3>Context &amp; Role</h3>
<p>
This project focuses on designing and validating user-centered dashboards for electric buses, with an emphasis on enhancing usability, safety, and driver experience in the Indian context. By addressing the unique challenges faced by bus drivers and stakeholders, the research integrates methodologies and theoretical frameworks from human-computer interaction (HCI), cognitive psychology, and user-centered design (UCD).


</p>
<h3>Challenges</h3>
<ul>
<li><strong>Complex Driver Tasks:</strong> Integrating real-time monitoring of battery levels, route navigation, and managing traffic hazards.</li>
<li><strong>Varying Road Conditions:</strong> Adapting the interface to diverse traffic patterns and unpredictable road behaviors.</li>
</ul>
<h3>Actions Taken</h3>
<ul>
<li>Developed a high-fidelity prototype through iterative design cycles: user research, wireframing, and simulator testing.</li>
<li>Integrated real-time sensor data (battery, motor status) into a simplified digital dashboard.</li>
<li>Conducted extensive user feedback sessions with bus drivers to refine the UI and minimize cognitive load.</li>
</ul>
<h3>Results</h3>
<ul>
<li>Reduced driver distraction and improved key response times (e.g., faster recognition of battery warnings).</li>
<li>Enhanced overall safety and user acceptance, proving the feasibility of large-scale EV bus deployment.</li>
</ul>
<h3>Lessons Learned</h3>
<ul>
<li>Merging hardware-electronics expertise with HCI is critical for an effective design.</li>
<li>Field observations and iterative feedback cycles are indispensable for real-world solutions.</li>
</ul>
</div>
</div>

<!-- Project 2: Banking Application for Financial Services -->
<div class="project">
<h2 class="project-title">Voiced based Banking Application for Financial Services</h2>
<img src="images/Banking_App.png" alt="Banking Application ASR" class="project-image" />
<div class="project-details">
<h3>Context &amp; Role</h3>
<p>
This project evaluates a voice-based Conversational AI prototype designed
to facilitate banking transactions—specifically, transferring Rs 5000 to a
beneficiary named "Ravi Kumar." Developed using HTML5, CSS3, Bootstrap, and
JavaScript, the prototype employs the Wizard-of-Oz technique to simulate
natural language understanding. The study involved remote usability testing
with 40 participants to assess the system's usability, attractiveness, and
intuitiveness.
</p>
<h3>Prototype Design &amp; Dialog Structure</h3>
<ul>
<li>
<strong>Application Flow:</strong> The system guides users through a
banking transaction via a flowchart-based interface.
</li>
<li>
<strong>Dialog Prompts:</strong> Three types of prompts are used:
<ul>
<li>
<em>Default Prompts:</em> Instructions provided at each step (e.g.,
"Please narrate your name" vs. "Your name?").
</li>
<li>
<em>Timeout Prompts:</em> Activated when no response is detected.
</li>
<li>
<em>Invalid-Input Prompts:</em> Played when incorrect inputs are given,
offering corrective guidance.
</li>
</ul>
</li>
<li>
<strong>Interface Variants:</strong> Two prototype versions were created:
<ul>
<li>
<em>Prototype Version A:</em> Features a dark background, detailed
default prompts, and a white orb that signals listening mode.
</li>
<li>
<em>Prototype Version B:</em> Uses a light background with minimal
default prompts and similar visual cues.
</li>
</ul>
</li>
</ul>

<h3>Challenges</h3>
<ul>
<li>Ensuring a natural dialogue flow while managing multi-turn conversations.</li>
<li>
Accurately capturing and processing domain-specific banking terminology.
</li>
<li>
Balancing the detail of dialog prompts with visual design to maintain
user engagement.
</li>
<li>
Conducting remote usability tests using video conferencing tools and a
Wizard-of-Oz setup.
</li>
</ul>

<h3>Actions Taken</h3>
<ul>
<li>
Implemented a Wizard-of-Oz framework, triggering pre-recorded dialog
prompts via designated keystrokes to simulate AI behavior.
</li>
<li>
Developed two distinct interface versions to assess the impact of dialog
prompt style and background design on user experience.
</li>
<li>
Conducted a comprehensive user study with 40 participants, using a series
of pre- and post-interaction questionnaires:
<ul>
<li>Single Ease Questionnaire (SEQ) to gauge task ease.</li>
<li>System Usability Scale (SUS) for overall usability.</li>
<li>
AttrakDiff’s attractiveness scale to measure efficiency, enjoyment, and
appeal.
</li>
<li>INTUI questionnaire to assess intuitiveness.</li>
</ul>
</li>
<li>
Analyzed both quantitative scores (e.g., SUS scores of 92.25 and 88.63)
and qualitative user feedback to determine system performance.
</li>
</ul>

<h3>Results &amp; Findings</h3>
<ul>
<li>
Participants rated the system as highly usable, attractive, and intuitive,
with SEQ and SUS scores indicating an excellent user experience.
</li>
<li>
Interface Version A received slightly higher ratings in usability and
overall satisfaction compared to Version B.
</li>
<li>
The study demonstrates that voice-based conversational AI can be a
viable interface for banking applications when backed by robust natural
language understanding.
</li>
</ul>

<h3>Lessons Learned</h3>
<ul>
<li>
Detailed, descriptive prompts may enhance user satisfaction, though minimal
prompts can also be effective depending on design context.
</li>
<li>
Remote usability testing using the Wizard-of-Oz method can yield valuable
insights, but further testing in real-world environments (e.g., at ATMs)
is recommended.
</li>
<li>
Balancing system performance, security, and natural language processing is
crucial for deploying conversational AI in sensitive domains like banking.
</li>
<li>
The findings support further investment in conversational AI for banking,
with potential extensions to enhance accessibility (e.g., for the visually
impaired) and support hands-free interactions.
</li>
</ul>
</div>
</div>


<!-- Project 4: AgroAssam (Agricultural Advisory System for Assam) -->
<div class="project">
<h2 class="project-title">
Enhancement of AGROASSAM: A Web Based Assamese Speech Recognition Application for Retrieving Agricultural Commodity Price and Weather Information
</h2>
<img src="images/agroassam.jpg" alt="AgroAssam Web Application" class="project-image" />
<div class="project-details">
<h3>Context &amp; Role</h3>
<p>
AgroAssam is a web-based speech recognition application developed to help users retrieve the latest prices of agricultural commodities and weather-related information in the Assamese language. By extracting commodity price data from the AGMARKNET website and weather data from the IMD website—both updated daily by the Government of India—the system adapts an existing phone-based voice query solution to a modern web interface.
</p>

<h3>Experimental Setup &amp; ASR Performance</h3>
<ul>
<li>
<strong>Data Collection:</strong>
Speech data was gathered in real field conditions from native Assamese speakers. This involved:
<ul>
<li>30 hours of isolated commodity and district names from 885 speakers.</li>
<li>3 hours of phonetically balanced sentences from 25 speakers.</li>
<li>Additional continuous speech recordings from 27 speakers (totaling 5658 files).</li>
</ul>
</li>
<li>
<strong>Acoustic Modeling:</strong>
Two modeling techniques were explored using the Kaldi toolkit:
<ul>
<li><em>GMM-HMM:</em> Achieved WERs of 10.31% for commodity names and 5.16% for district names.</li>
<li><em>DNN-HMM:</em> Improved WERs to 7.79% for commodities and 4.98% for district names.</li>
</ul>
</li>
<li>
<strong>Noise Handling:</strong>
The system employed Zero Frequency Filtered Signal (ZFFS) techniques to effectively separate foreground speech from background noise.
</li>
</ul>

<h3>Application Design</h3>
<ul>
<li>
On accessing the application URL, users are greeted with a welcome prompt and asked to state the desired district.
</li>
<li>
Upon successful recognition of the district, users choose between retrieving agricultural commodity prices or weather information.
</li>
<li>
For commodity queries, after the commodity name is recognized, the system checks the district-commodity combination in the database and displays the modal price.
</li>
<li>
For weather queries, the system retrieves current and upcoming weather details for the specified district.
</li>
<li>
The back-end ASR modules are developed with state-of-the-art acoustic modeling approaches, ensuring accurate recognition despite channel and noise variations.
</li>
</ul>

<h3>Results &amp; Impact</h3>
<ul>
<li>
The DNN-HMM based system significantly reduced the word error rate, leading to more accurate recognition of both commodity and district names.
</li>
<li>
The integration into a web interface demonstrates that systems designed for telephonic voice queries can be effectively adapted for web-based platforms without compromising performance.
</li>
<li>
AgroAssam has the potential for deployment in public kiosks and digital information centers, thereby supporting farmers with timely access to essential agricultural and weather information in their native language.
</li>
</ul>

<h3>Conclusion</h3>
<p>
AgroAssam successfully bridges the gap between traditional phone-based voice query systems and modern web interfaces. By leveraging advanced ASR techniques and a robust experimental setup, the project provides a reliable solution for retrieving vital information in Assamese, thus empowering the agrarian community and contributing to the digital transformation initiatives in India.
</p>
</div>
</div>



<!-- Project 5: SIFA (Speech Interface for Form-Filling Application) -->
<div class="project">
<h2 class="project-title">SIFA (Speech Interface for Form-Filling Application)</h2>
<img src="images/SiFA.png" alt="SIFA Form-Filling Application" class="project-image" />
<div class="project-details">
<h3>Context &amp; Role</h3>
<p>
Developed at IIT Bhubaneswar, SIFA automates form-filling in five Indian languages (Hindi, Odia, Bengali, Assamese, Telugu).
I contributed to designing the acoustic model for Odia language and integrating a custom lexicon for all the respective fields of the form.
</p>
<h3>Challenges</h3>
<ul>
<li><strong>Data Inconsistency:</strong> Handling varied audio quality and misaligned transcripts.</li>
<li><strong>Local Vocabulary:</strong> Incorporating domain-specific terms, such as district names and local expressions.</li>
</ul>
<h3>Actions Taken</h3>
<ul>
<li>Automated preprocessing pipelines to standardize sampling rates and clean transcripts.</li>
<li>Developed and integrated a custom lexicon into an end-to-end or CTC-based ASR model.</li>
<li>Employed shallow fusion with a domain-adapted language model to enhance recognition accuracy.</li>
</ul>
<h3>Results</h3>
<ul>
<li>Achieved a significant reduction in Word Error Rate (WER), dropping from 30% to approximately 12%.</li>
<li>Improved the user experience, making form completion easier and faster for non-technical users.</li>
</ul>
<h3>Lessons Learned</h3>
<ul>
<li>High data quality is paramount in speech tasks; even minor errors can have a large impact.</li>
<li>Domain adaptation in both acoustic and language modeling dramatically improves handling of local vocabulary.</li>
</ul>
</div>
</div>
</div>

<script>
// Optional JavaScript to allow toggling project details when the title is clicked.
// This improves usability on mobile devices.
document.querySelectorAll('.project-title').forEach(title => {
title.addEventListener('click', () => {
const details = title.nextElementSibling.nextElementSibling;
details.style.display = (details.style.display === 'none' || details.style.display === '') ? 'block' : 'none';
});
});
</script>
</body>
</html>
Binary file added images/.DS_Store
View file
Open in desktop
Binary file not shown.
Binary file added images/Banking_App.png
View file
Open in desktop
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added images/IITG_logo.png
View file
Open in desktop
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added images/SiFA.png
View file
Open in desktop
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added images/agroassam.jpg
View file
Open in desktop
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added images/cockpit_bus.jpg
View file
Open in desktop
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added images/lipsa.jpeg
View file
Open in desktop
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added images/myphoto.jpeg
View file
Open in desktop
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading