SIH26052/Miscellaneous

Real-time AI defence noise cancellation hardware

A hardware prototype that uses an AI model on an edge device to remove defence noises like gunshots from audio in real time.

DRDO · Department of Defence Production /IDEX · Hardware

Teams already in: 1/500almost everyone who enters · read 1 hour ago
Buildable in 36 hours: LowOur estimate, from their wording
Hard blockers: 3Restricted data, Needs hardware, No dataset given
Submissions close: 15 Sept9 days left

Make this one of our two Compare with others

Signing in saves it for your whole team — everyone on your invite link sees the same two entries. Anything you shortlisted while signed out comes with you.

Submit on sih.gov.in

Whether this suits your team

What to know before you start

Potential concern: needs data you may not get.
Potential concern: needs physical hardware.
Potential concern: no dataset provided.

What you would have to build

Decomposed from what the description asks for. Nothing added.

01
Dataset Generation Pipeline
Combine clean speech with defence noise datasets at varying SNR levels to create training pairs.
02
AI Noise Suppression Model
Train a machine learning model using time-frequency representations and perceptual loss functions.
03
Edge Inference Engine
Optimize and deploy the trained model onto embedded hardware for real-time processing.
04
Hardware Integration
Connect microphones and headphones to the embedded platform to test live noise cancellation.

What they ask for, and what they leave open

Both columns are read off the brief's own wording. Nothing here is inferred from the ministry's name.

They state

The jury will test whether the system achieves SNR above 15 dB, STOI above 0.85, and PESQ above 2.5 while running in real time on edge hardware.

They never say

specific defence noise audio samples to use for training
exact latency threshold in milliseconds for real-time performance

A jury can still ask about these. Decide them deliberately rather than by accident.

What they'll ask you

Generated from the brief's own wording and the competition's published rules — never from a guess about what this ministry prefers.

Specific defence noise audio samples to use for training?
The brief never answers this, so a panel will. Whatever you decide, say it the same way twice.
Exact latency threshold in milliseconds for real-time performance?
The brief never answers this, so a panel will. Whatever you decide, say it the same way twice.
Has any part of this been shown at a previous event, hackathon or college project?
The guidelines are explicit: your solution must not have appeared in any previous event or programme, of any sort. A recycled project is what a team under time pressure reaches for.

8 more— the ones a panel gets to if there is time

The brief asks for dataset generation pipeline. How would you build that?
Decoded from SIH26052 itself — Combine clean speech with defence noise datasets at varying SNR levels to create training pairs. The brief asks for it by name.

Before you commit

Each one is quoted from a gap in the brief, not a guess about your team.

Needs physical hardware
Listed as a hardware problem statement, so a working demo needs physical components you have to source yourself.
No dataset provided
The description depends on real data, and the organisers have not attached a dataset link.
Needs data you may not get
The description requires curated defence noise datasets such as gunshots and artillery fire which students cannot easily obtain.

The data

What the organisers attached, and what the brief assumes you can get.

Dataset from the organisers: None attached
Does the brief need data?: Yes, and none is attached — finding or generating it is part of the work.

Also from DRDO

Same organisation, same year. Reading two of theirs tells you more about what they care about than reading one.

Take this to an AI

Pick what you are about to do and copy the prompt. It carries the organisers' own wording, the constraints they never spell out, and an instruction not to invent requirements they never set.

Who has this problem, what already exists, and what you would have to find out.

# Context: India's Smart India Hackathon 2026

I am on a student team entering SIH 2026. Problem statement SIH26052, set by DRDO.
Its official title, word for word: "To develop an AI/ML-enabled adaptive noise cancellation (ANC) system that effectively suppresses stationary, non-stationary, and impulsive defence noises while maintaining high speech intelligibility and real-time performance on embedded hardware."
Theme: Miscellaneous. Category: hardware.

In plain terms: A hardware prototype that uses an AI model on an edge device to remove defence noises like gunshots from audio in real time.

## The organisers' full description, verbatim

• Background: In defence and mission-critical communication systems, reliable speech transmission is severely affected by diverse acoustic disturbances such as gunshots, artillery fire, helicopter rotor noise, armored vehicle sound and emergency sirens. Traditional signal processing techniquesâ€”like spectral subtraction, Wiener filtering, and classical LMS-based ANCâ€”are limited in handling highly dynamic and non-linear noise environments. These methods assume stationary noise characteristics and often introduce artifacts or speech distortion under rapidly changing conditions. Recent advancements in Artificial Intelligence and Machine Learning (AI/ML) have transformed the field of speech enhancement and ANC. Deep learning models and time-domain architectures are capable of learning complex spectral-temporal patterns directly from data. These models significantly outperform conventional approaches in terms of perceptual quality (PESQ), intelligibility (STOI), and noise suppression (SNR). Additionally, the rise of edge AI platforms enables deployment of such models on embedded systems for real-time applications. • Description: The proposed system integrates AI/ML-driven noise suppression with adaptive filtering to create a robust ANC pipeline. The development begins with dataset generation, where clean speech data is combined with curated defence noise datasets (gunshots, drones, artillery, vehicle engines, wind, etc.) at varying SNR levels. This synthetic data generation ensures coverage of both stationary and impulsive noise scenarios. The training pipeline involves transforming audio into time-frequency representations (e.g., STFT spectrograms) or directly using raw waveform inputs. Models process both full-band and sub-band features to capture global and local dependencies. while its also operates in the complex domain to preserve phase information. Training is performed using loss functions such as SI-SNR, L1/L2 loss, and perceptual loss, with evaluation metrics including SNR, STOI, and PESQ. Data augmentation techniques (random noise mixing, reverberation, clipping) are applied to improve generalization. During inference, the trained model processes incoming noisy audio in real time, estimating a mask or directly reconstructing enhanced speech. The system can optionally include a lightweight adaptive filter (e.g., LMS) for residual noise suppression. For prototype demonstration, the trained model is deployed on embedded/edge hardware such as DSPs or AI-enabled SoCs (e.g., NVIDIA Jetson AGX Orin 64GB Developer Kit or similar platforms). Optimization techniques like quantization, pruning, and ONNX / TensorRT conversion are applied to meet latency and power constraints. The system is integrated with microphones (primary + reference) and headphones/communication units to validate real-time ANC performance in practical environments • Expected Solution: The final solution is a hybrid AI-driven ANC system capable of operating in real-time and handling diverse noise environments, including impulsive and highly dynamic defence scenarios. It should include: • A scalable dataset pipeline for generating realistic noisy-clean speech pairs • A state-of-the-art AI/ML model trained for robust noise suppression • A training framework with optimized hyper-parameters and perceptual loss functions • A real-time inference engine deployable on edge hardware • A prototype system demonstrating live noise cancellation using microphones / headset integration The system is expected to achieve significant performance improvements, targeting SNR > 15 dB, STOI > 0.85, and PESQ > 2.5, while maintaining low latency suitable for real-time communication. This solution will enable reliable and intelligible communication in defence, aerospace, and high-noise industrial environments.

## What the brief never says

- specific defence noise audio samples to use for training
- exact latency threshold in milliseconds for real-time performance
## Constraints that are not negotiable

- The judged build is a prototype demonstrated in roughly 36 hours by students, not a product.
- A jury evaluates it against this problem statement's own wording, not against general merit.
- We submit on sih.gov.in; the problem statement number and title above must match exactly.
- Your solution must not have appeared in any previous event or programme, of any sort.
- This is a hardware problem statement, so a demo needs physical components we source ourselves.
- No dataset was attached, and the brief depends on data. Finding or generating it is part of the work.
- Known obstacles in the brief: Needs hardware; Restricted data.

## What I want from you

1. Who actually has this problem in India, and what they do about it today.
2. What already exists — government systems, open-source projects, published research — that we should not rebuild.
3. For each item under 'what the brief never says', what the realistic answer is likely to be and how I could verify it.
4. The two or three things about this domain that a student team would get wrong without local knowledge.
## How to answer

- Everything above between quotation marks is the organisers' own wording. Treat it as the requirement.
- Do NOT invent requirements the brief does not state. If something matters and is not stated, say so and ask me, rather than assuming.
- Where you are inferring rather than reading, mark it as your inference.
- Do not guess what this ministry wants from its name. Its wording above is the only evidence.

---
Problem statement facts assembled by Wynit from DRDO's published brief for SIH 2026.
The plain-English summary, the list of parts and the evaluator read are our interpretation of that text; the quoted title and the full description are theirs.

The government's original description (508 words)

• Background: In defence and mission-critical communication systems, reliable speech transmission is severely affected by diverse acoustic disturbances such as gunshots, artillery fire, helicopter rotor noise, armored vehicle sound and emergency sirens. Traditional signal processing techniquesâ€”like spectral subtraction, Wiener filtering, and classical LMS-based ANCâ€”are limited in handling highly dynamic and non-linear noise environments. These methods assume stationary noise characteristics and often introduce artifacts or speech distortion under rapidly changing conditions. Recent advancements in Artificial Intelligence and Machine Learning (AI/ML) have transformed the field of speech enhancement and ANC. Deep learning models and time-domain architectures are capable of learning complex spectral-temporal patterns directly from data. These models significantly outperform conventional approaches in terms of perceptual quality (PESQ), intelligibility (STOI), and noise suppression (SNR). Additionally, the rise of edge AI platforms enables deployment of such models on embedded systems for real-time applications. • Description: The proposed system integrates AI/ML-driven noise suppression with adaptive filtering to create a robust ANC pipeline. The development begins with dataset generation, where clean speech data is combined with curated defence noise datasets (gunshots, drones, artillery, vehicle engines, wind, etc.) at varying SNR levels. This synthetic data generation ensures coverage of both stationary and impulsive noise scenarios. The training pipeline involves transforming audio into time-frequency representations (e.g., STFT spectrograms) or directly using raw waveform inputs. Models process both full-band and sub-band features to capture global and local dependencies. while its also operates in the complex domain to preserve phase information. Training is performed using loss functions such as SI-SNR, L1/L2 loss, and perceptual loss, with evaluation metrics including SNR, STOI, and PESQ. Data augmentation techniques (random noise mixing, reverberation, clipping) are applied to improve generalization. During inference, the trained model processes incoming noisy audio in real time, estimating a mask or directly reconstructing enhanced speech. The system can optionally include a lightweight adaptive filter (e.g., LMS) for residual noise suppression. For prototype demonstration, the trained model is deployed on embedded/edge hardware such as DSPs or AI-enabled SoCs (e.g., NVIDIA Jetson AGX Orin 64GB Developer Kit or similar platforms). Optimization techniques like quantization, pruning, and ONNX / TensorRT conversion are applied to meet latency and power constraints. The system is integrated with microphones (primary + reference) and headphones/communication units to validate real-time ANC performance in practical environments • Expected Solution: The final solution is a hybrid AI-driven ANC system capable of operating in real-time and handling diverse noise environments, including impulsive and highly dynamic defence scenarios. It should include: • A scalable dataset pipeline for generating realistic noisy-clean speech pairs • A state-of-the-art AI/ML model trained for robust noise suppression • A training framework with optimized hyper-parameters and perceptual loss functions • A real-time inference engine deployable on edge hardware • A prototype system demonstrating live noise cancellation using microphones / headset integration The system is expected to achieve significant performance improvements, targeting SNR > 15 dB, STOI > 0.85, and PESQ > 2.5, while maintaining low latency suitable for real-time communication. This solution will enable reliable and intelligible communication in defence, aerospace, and high-noise industrial environments.