Overview
Spectral subtraction estimates noise during quiet regions, removes that estimate from each frequency bin, and reconstructs the signal.
CoreSource checked
Spectral Subtraction
Reduces noise by subtracting an estimated noise spectrum from the observed spectrum.
Quick Facts
Compact metadata for implementation and discovery.
- Category
- Signal Processing
- Difficulty
- Intermediate
- Family
- Noise Reduction
- Tier
- Core
- Status
- Verified
- Review
- Source Checked
- Sources
- 1
- Formulas
- 1
- Relationships
- 1
- Code example
- Ready
- Visualization
- Ready
Core Concepts
noise spectrumstft framemagnitude subtractionsignal reconstruction
Quick facts
Complexity
Runtime and memory behavior at a glance.
Best
O(n log n)
Average
O(frames * n log n)
Worst
O(frames * n log n)
Space
O(frame size)
When to Use
- Use when filtering noisy signals needs noise spectrum.
- Use when the input matches the assumptions behind noise Reduction.
When Not to Use
- Avoid when sampling rate, phase, or boundary assumptions are unknown.
- Avoid when a simpler algorithm gives the required result with less setup.
What It Does
- Reduces noise by subtracting an estimated noise spectrum from the observed spectrum
- Uses noise spectrum and stft frame to guide the work.
- Produces filtered signal.
Use Cases
- Filtering noisy signals
- Spectral analysis
- Audio and sensor processing
Inputs
- Sampled signal
- Filter or transform parameters
Outputs
- Filtered signal
- Spectrum or feature representation
Key Formulas (1)
Magnitude estimate
cleanmag = max(observedmag − noisemag, floor)
clean_mag = max(observed_mag - noise_mag, floor)Reduces each spectral bin while avoiding negative magnitudes.
Pseudocode
- 1.Validate sampling rate, window, boundary, and parameter choices
- 2.Prepare the signal state, coefficients, or transform workspace
- 3.Apply the filter, transform, or measurement rule to each sample or frame
- 4.Handle boundaries and normalization consistently
- 5.Return the filtered signal, coefficients, or feature values
Canonical Example
- Input
- Spectral Subtraction
- Output
- Filtered signal
- Explanation
- Spectral Subtraction applies noise spectrum to produce filtered signal.
Implementation Notes
- Document sample rate, windowing, and normalization conventions.
- Keep the noise spectrum step separate enough to test independently.
- Keep sampling rate, window size, latency, and boundary conventions explicit in tests.
Common Pitfalls
- Boundary handling and normalization choices can change the interpretation of the result.
- Test edge cases, not only clean examples.
- Ignoring sampling rate, boundary handling, or phase behavior can make the output misleading.
Interactive Mechanism Walkthrough
Iterative Convergence & State TrajectoryShow the input signal beside the filtered, transformed, or reconstructed output.
Step 1 of 5: Validate sampling rate, window, boundary, and parameter choices
signal-processing-mechanismNotes
Spectral Subtraction should be used with the assumptions and tradeoffs of noise Reduction in mind.
Sources (1)
What each reference supports for this entry.
Explore Next
Good next jumps from the relationship graph, ranked for useful discovery.
Relationships
View full relationship pageSpectral subtraction estimates and removes noise in the frequency domain.
Related Algorithms
Tags
Signal ProcessingNoise ReductionSpectral AnalysisAudio Processing