🔇

Noise Canceller

Browser-based noise cancelling with AudioWorklet noise generation, NLMS adaptive predictor ANC, Wiener spectral suppression for speech and broadband noise, A-weighted analysis, 5-band EQ, and adaptive masking.

Noise Canceller

Analyze ambient noise with your microphone and generate adaptive masking sounds through your headphones.

Ambient Noise Analysis

Raw

-60.0 dB

dB(A)

-60.0 dB(A)

dB(A) applies A-weighting to approximate perceived loudness. Adaptive mode uses this for accurate tracking.

Presets

Masking Noise

Noise Type

–6 dB/octave — deep rumble for traffic, HVAC, fans.

Master Volume — 40%

Adaptive Mode

Auto-adjusts masking using A-weighted ambient analysis

5-Band Equalizer

Sub

80 Hz

Low

320 Hz

Mid

1k Hz

Presence

3.2k Hz

Air

10k Hz

Active Noise Cancellation

How the Noise Canceller Works

The Noise Canceller uses your browser's Web Audio API with AudioWorklet processors running on a dedicated audio rendering thread. It captures ambient sound through your microphone, analyses it in real time, and generates both adaptive masking noise and active anti-noise through your headphones.

Masking Noise Types

White noise — flat spectrum, masks high-pitched and variable sounds.
Pink noise — –3 dB/octave via Paul Kellet's 7-stage filter. Natural-sounding, effective for speech masking in the 300–3,000 Hz band.
Brown noise — –6 dB/octave. Deep rumble that blocks traffic, HVAC, and fans. Research suggests low-frequency noise below 500 Hz reduces stress.

Active Noise Cancellation

Three ANC modes run entirely inside AudioWorklet processors for minimum latency:

Phase Inversion Mode

Captures mic audio, inverts its phase through a cascaded 18 dB/octave lowpass filter, and outputs the anti-noise. Simple and immediate, but limited by system latency — effective only for frequencies below roughly 1/(2 × latency). At typical browser latency of 14–40 ms, this works for sub-bass content.

NLMS Adaptive Predictor Mode

The Normalized Least Mean Squares (NLMS) adaptive filter overcomes the latency barrier. It works by learning the periodic structure of ambient noise:

Training: The filter uses samples from D samples ago (where D equals the measured system latency) to predict the current sample. The prediction error is used to update the filter weights via the NLMS algorithm: W = W + μ · e(n) · u / (||u||² + ε).
Prediction: Using the same learned weights but with current samples, the filter predicts what the noise will sound like D samples in the future.
Cancellation: This prediction is inverted and output as anti-noise. By the time it reaches your ears (D samples later), it arrives in phase with the actual noise.

For periodic noise (fans, AC, hums, engine drone), the filter converges within seconds and can effectively cancel the tonal components. A convergence meter shows real-time MSE (mean squared error) — when it drops below 0.01, cancellation is active. The filter length controls how many frequency components can be modelled, while the learning rate controls the speed-stability tradeoff.

Spectral Suppression Mode (Wiener Filter)

The most versatile mode, effective against non-periodic noise like speech, typing, keyboard clicks, and broadband hiss. It uses a 1024-point FFT with 75% overlap (256-sample hops) to analyze the frequency spectrum of incoming audio.

Noise estimation: During the first ~0.3 seconds (15 frames), the processor builds a noise power spectrum estimate. After initialization, a Voice Activity Detector (VAD) using energy and spectral flatness analysis determines which frames contain only noise. The noise estimate updates continuously during noise-only frames.
Decision-directed Wiener filter: For each frequency bin, the processor computes the a priori SNR using temporal smoothing (α_dd = 0.98). The Wiener gain G(k) = ξ(k) / (ξ(k) + 1) determines how much each frequency is attenuated.
Musical noise mitigation: A spectral floor prevents over-suppression artifacts, and 3-point frequency smoothing reduces isolated spectral peaks that cause “musical noise” — the tinkling artifact common in basic spectral subtraction.
Overlap-add synthesis: The processed spectrum is inverse-FFT'd and overlap-added with a Hann window for artifact-free reconstruction.

Ultra-Low-Latency Pipeline

The AudioContext uses latencyHint: 0 (numeric zero) to request the absolute minimum latency the platform supports. The mic stream disables echo cancellation, noise suppression, and auto gain control to eliminate processing latency. Mono input (channelCount: 1) halves the processing load. The system measures and displays baseLatency + outputLatency so you can see your actual round-trip performance (Firefox typically achieves ~14 ms, Chrome ~19–40 ms).

A-Weighted Metering & Adaptive Mode

Dual meters show raw dB and A-weighted dB(A) per ISO 61672-1. The adaptive mode uses dB(A) with an attack/release envelope for natural masking volume adjustments.

Privacy

All processing runs in your browser. No audio is recorded, stored, or transmitted. The mic stream and all AudioWorklet processors are terminated when you stop the tool.

Loading interactive tool...

Share this tool

How to Use the Noise Canceller

1
Enter your values
Open the Noise Canceller and fill in the required input fields with your numbers or selections.
2
Review the calculation
The tool automatically computes the result as you type. Double-check your inputs to ensure accuracy.
3
Interpret your results
Review the calculated output along with any breakdowns, charts, or explanations provided to understand what the numbers mean for your situation.

Sources & Verification

U.S. Department of Education UNESCO Education Data

Published by ConvertCrunch Editorial Team | Our Methodology

Frequently Asked Questions

What is the Noise Canceller?

The Noise Canceller is a free browser-based tool on ConvertCrunch. Browser-based noise cancelling with AudioWorklet noise generation, NLMS adaptive predictor ANC, Wiener spectral suppression for speech and broadband noise, A-weighted analysis, 5-band EQ, and adaptive masking. It requires no downloads, installations, or account signups. Simply enter your values and get instant, accurate results. The tool is designed for quick calculations and informed decision-making, whether you are a professional, student, or everyday user looking for reliable answers.

How do I use the Noise Canceller?

Using the Noise Canceller is straightforward. Enter your values into the input fields provided on the page, then calculate or adjust parameters to explore scenarios. Most processing happens locally in your browser. If a feature uses a third-party service, the tool identifies that connection and the privacy policy explains it. Most users get the answers they need in under a minute.

Is the Noise Canceller free to use?

Yes, the Noise Canceller is completely free to use with no account signup, email requirement, or premium tier. Most calculations run locally in your browser. Features that depend on live data or a third-party service require a network connection and are identified in the tool. You can use it as many times as you need for personal, educational, or professional purposes.

How accurate is the Noise Canceller?

The Noise Canceller uses standard academic formulas and grading scales. Results depend on the accuracy of the information you enter. Grading policies, credit weighting, and academic standards vary by institution, so verify specific requirements with your school's registrar or academic advisor. This tool is designed for planning and estimation, not as an official academic record.

Embed This Tool

Add this calculator to your website with a simple iframe.

Related Tools

🇮🇳

India CGPA Calculator

Calculate your Indian CGPA and SGPA on the 10-point scale. Supports CBCS grading used by UGC-affiliated universities.

🇵🇰

Pakistan GPA Calculator

Calculate your Pakistani university CGPA on the 4.0 scale. Supports the HEC-standard grading system used by Pakistani universities.

🇬🇧

UK Grade Calculator

Calculate your UK university degree classification from module marks. Supports First, 2:1, 2:2, Third, and percentage-based grading.

🎯

Eisenhower Matrix

Interactive urgent/important priority grid. Add tasks, drag between quadrants, and visualize where your time should go.

📖

Readability Score Checker

Analyze text readability with Flesch-Kincaid, Gunning Fog, SMOG, Coleman-Liau, and Flesch Reading Ease scores.

📅

Study Time Planner

Allocate study hours across subjects based on exam weight and difficulty. Visual breakdown with daily targets.

📝

Citation Generator (APA, MLA, Chicago)

Generate APA 7th, MLA 9th, and Chicago 17th citations from manual input. Supports books, journals, websites, and conference papers.

📐

Time Blocking Planner

Plan your day in focused time blocks. Visual daily schedule with color-coded categories for deep work, meetings, breaks, and more.

How the Noise Canceller Works

Masking Noise Types

White noise — flat spectrum, masks high-pitched and variable sounds.
Pink noise — –3 dB/octave via Paul Kellet's 7-stage filter. Natural-sounding, effective for speech masking in the 300–3,000 Hz band.
Brown noise — –6 dB/octave. Deep rumble that blocks traffic, HVAC, and fans. Research suggests low-frequency noise below 500 Hz reduces stress.

Active Noise Cancellation

Three ANC modes run entirely inside AudioWorklet processors for minimum latency:

Phase Inversion Mode

NLMS Adaptive Predictor Mode

The Normalized Least Mean Squares (NLMS) adaptive filter overcomes the latency barrier. It works by learning the periodic structure of ambient noise:

Training: The filter uses samples from D samples ago (where D equals the measured system latency) to predict the current sample. The prediction error is used to update the filter weights via the NLMS algorithm: W = W + μ · e(n) · u / (||u||² + ε).
Prediction: Using the same learned weights but with current samples, the filter predicts what the noise will sound like D samples in the future.
Cancellation: This prediction is inverted and output as anti-noise. By the time it reaches your ears (D samples later), it arrives in phase with the actual noise.

Spectral Suppression Mode (Wiener Filter)

Noise estimation: During the first ~0.3 seconds (15 frames), the processor builds a noise power spectrum estimate. After initialization, a Voice Activity Detector (VAD) using energy and spectral flatness analysis determines which frames contain only noise. The noise estimate updates continuously during noise-only frames.
Decision-directed Wiener filter: For each frequency bin, the processor computes the a priori SNR using temporal smoothing (α_dd = 0.98). The Wiener gain G(k) = ξ(k) / (ξ(k) + 1) determines how much each frequency is attenuated.
Musical noise mitigation: A spectral floor prevents over-suppression artifacts, and 3-point frequency smoothing reduces isolated spectral peaks that cause “musical noise” — the tinkling artifact common in basic spectral subtraction.
Overlap-add synthesis: The processed spectrum is inverse-FFT'd and overlap-added with a Hann window for artifact-free reconstruction.

Ultra-Low-Latency Pipeline

A-Weighted Metering & Adaptive Mode

Dual meters show raw dB and A-weighted dB(A) per ISO 61672-1. The adaptive mode uses dB(A) with an attack/release envelope for natural masking volume adjustments.

Privacy

All processing runs in your browser. No audio is recorded, stored, or transmitted. The mic stream and all AudioWorklet processors are terminated when you stop the tool.