Project

# Title Team Members TA Documents Sponsor
45 AI-based Meeting Transcription Device
Chang Liu
Gao Gao
Ziyang Huang
Jiankun Yang design_document1.docx
final_paper1.pdf
other1.pdf
other2.txt
photo2.jpg
photo3.jpg
photo1.jpg
presentation1.pptx
proposal1.pdf
## Team Members:
- **Ziyang Huang** (ziyangh3)
- **Gao Gao** (xgao54)
- **Chang Liu** (changl21)

## Problem

During the pandemic, we found Zoom’s live transcription very useful, as it helped the audience catch up quickly with the lecturer. In many professional and academic settings, real-time transcription of spoken communication is essential for note-taking. Additionally, individuals with hearing impairments face challenges in following spoken conversations, especially in environments where captions are unavailable.

Existing solutions, such as Zoom’s live transcription or mobile speech-to-text apps, require an internet connection and are often tied to specific platforms. To address this, we propose a standalone, portable transcription device that can capture, transcribe, and display spoken text in real time. The device will be helpful since it provides a distraction-free way to record and review conversations without relying on a smartphone or laptop.

## Solution

Our **Smart Meeting Transcription Device** will be a portable, battery-powered device that records with a microphone, converts speech into real-time text, and displays it on an LCD screen. The system consists of the following key components:

1. **A microphone module** to capture audio input.
2. **A speech processing unit** (Jetson Nano/Raspberry Pi/Arduino) running the Vosk speech-to-text model to transcribe the captured speech.
3. **An STM32 microcontroller**, which serves as the central controller for managing user interactions, processing text display, and storing transcriptions.
4. **An LCD screen** to display transcriptions in real-time.
5. **External memory** (SD card or NOR flash) for saving transcribed conversations.
6. **A power system** (battery with efficient power management) to enable portability.

---

## Solution Components

### **Subsystem 1: Speech Processing Unit**
- **Function:** Captures audio and converts speech into text using an embedded speech-to-text model.
- **Microphone Module:** Adafruit Electret Microphone Amplifier (MAX9814)
- **Processing Board:** Jetson Nano / Raspberry Pi 4B
- **Speech Recognition Model:** Vosk Speech-to-Text Model
- **Memory Expansion (if required):** SD card (SanDisk Ultra 32GB)

### **Subsystem 2: STM32 Central Controller**
- **Function:** Manages the user interface, processes the transcribed text, and sends data to the LCD screen.
- **Microcontroller:** STM32F4 Series MCU
- **Interface Components:** Buttons for navigation and text saving
- **Memory Module:** SPI-based NOR Flash (W25Q128JV)

### **Subsystem 3: Display Module**
- **Function:** Displays real-time transcriptions and allows users to scroll through previous text.
- **LCD Screen:** 2.8-inch TFT Display (ILI9341)
- **Controller Interface:** SPI Communication with STM32

### **Subsystem 4: Power Management System**
- **Function:** Provides reliable and portable power for all components.
- **Battery:** 3.7V Li-ion Battery (Adafruit 2500mAh)
- **Power Regulation:** TP4056 Li-ion Charger + 5V Boost Converter
- **Power Optimization:** Sleep mode for STM32 to enhance battery life

---

## **Criterion for Success**
1. The device must accurately transcribe speech to text with reasonable latency.
2. The LCD screen must display real-time transcriptions clearly.
3. The STM32 must successfully manage system operations and communicate with peripheral components.
4. The system should support local storage for saving transcriptions.
5. The battery life should last at least **2-3 hours** under normal usage conditions.

Illini Voyager

Cameron Jones, Christopher Xu

Featured Project

# Illini Voyager

Team Members:

- Christopher Xu (cyx3)

- Cameron Jones (ccj4)

# Problem

Weather balloons are commonly used to collect meteorological data, such as temperature, pressure, humidity, and wind velocity at different layers of the atmosphere. These data are key components of today’s best predictive weather models, and we rely on the constant launch of radiosondes to meet this need. Most weather balloons cannot control their altitude and direction of travel, but if they could, we would be able to collect data from specific regions of the atmosphere, avoid commercial airspaces, increase range and duration of flights by optimizing position relative to weather forecasts, and avoid pollution from constant launches. A long endurance balloon platform also uniquely enables the performance of interesting payloads, such as the detection of high energy particles over the Antarctic, in situ measurements of high-altitude weather phenomena in remote locations, and radiation testing of electronic components. Since nearly all weather balloons flown today lack the control capability to make this possible, we are presented with an interesting engineering challenge with a significant payoff.

# Solution

We aim to solve this problem through the use of an automated venting and ballast system, which can modulate the balloon’s buoyancy to achieve a target altitude. Given accurate GPS positioning and modeling of the jetstream, we can fly at certain altitudes to navigate the winds of the upper atmosphere. The venting will be performed by an actuator fixed to the neck of the balloon, and the ballast drops will consist of small, biodegradable BBs, which pose no threat to anything below the balloon. Similar existing solutions, particularly the Stanford Valbal project, have had significant success with their long endurance launches. We are seeking to improve upon their endurance by increasing longevity from a power consumption and recharging standpoint, implementing a more capable altitude control algorithm which minimizes helium and ballast expenditures, and optimizing mechanisms to increase ballast capacity. With altitude control, the balloon has access to winds going in different directions at different layers in the atmosphere, making it possible to roughly adjust its horizontal trajectory and collect data from multiple regions in one flight.

# Solution Components

## Vent Valve and Cut-down (Mechanical)

A servo actuates a valve that allows helium to exit the balloon, decreasing the lift. The valve must allow enough flow when open to slow the initial ascent of the balloon at the cruising altitude, yet create a tight seal when closed. The same servo will also be able to detach or cut down the balloon in case we need to end the flight early. A parachute will deploy under free fall.

## Ballast Dropper (Mechanical)

A small DC motor spins a wheel to drop [biodegradable BBs](https://www.amazon.com/Force-Premium-Biodegradable-Airsoft-Ammo-20/dp/B08SHJ7LWC/). As the total weight of the system decreases, the balloon will gain altitude. This mechanism must drop BBs at a consistent weight and operate for long durations without jamming or have a method of detecting the jams and running an unjamming sequence.

## Power Subsystem (Electrical)

The entire system will be powered by a few lightweight rechargeable batteries (such as 18650). A battery protection system (such as BQ294x) will have an undervoltage and overvoltage cutoff to ensure safe voltages on the cells during charge and discharge.

## Control Subsystem (Electrical)

An STM32 microcontroller will serve as our flight computer and has the responsibility for commanding actuators, collecting data, and managing communications back to our ground console. We’ll likely use an internal watchdog timer to recover from system faults. On the same board, we’ll have GPS, pressure, temperature, and humidity sensors to determine how to actuate the vent valve or ballast.

## Communication Subsystem (Electrical)

The microcontroller will communicate via serial to the satellite modem (Iridium 9603N), sending small packets back to us on the ground with a minimum frequency of once per hour. There will also be a LED beacon visible up to 5 miles at night to meet regulations. We have read through the FAA part 101 regulations and believe our system meets all requirements to enable a safe, legal, and ethical balloon flight.

## Ground Subsystem (Software)

We will maintain a web server which will receive location reports and other data packets from our balloon while it is in flight. This piece of software will also allow us to schedule commands, respond to error conditions, and adjust the control algorithm while in flight.

# Criterion For Success

We aim to launch the balloon a week before the demo date. At the demo, we will present any data collected from the launch, as well as an identical version of the avionics board showing its functionality. A quantitative goal for the balloon is to survive 24 hours in the air, collect data for that whole period, and report it back via the satellite modem.

![Block diagram](https://i.imgur.com/0yazJTu.png)