NeuralParametricEQ<T>

Models & Types · AiDotNet.Audio.Effects

Neural Parametric EQ model for automatic equalization (Steinmetz et al., 2022).

Inheritance: NeuralNetworkBase<T> → AudioNeuralNetworkBase<T> → NeuralParametricEQ<T>

Implements: IAudioEnhancer<T>

For Beginners

Imagine you have audio that sounds too bassy or too bright. Instead of manually turning EQ knobs, this model listens to the audio and automatically figures out the right EQ settings. It predicts gain (louder/quieter), frequency (which range to adjust), and Q (how narrow the adjustment is) for each band.

Usage:

How It Works

Neural Parametric EQ uses a neural network to automatically predict optimal parametric EQ settings (gain, frequency, Q for each band) to match a target frequency response. It analyzes input audio and outputs the parameters for a cascaded biquad filter bank, enabling automatic mastering, hearing aid fitting, and frequency matching.

Constructors

Constructor Summary
NeuralParametricEQ(NeuralNetworkArchitecture<T> architecture, NeuralParametricEQOptions options, IGradientBasedOptimizer<T, Tensor<T>, Tensor<T>> optimizer) Creates a Neural Parametric EQ model in native training mode.
NeuralParametricEQ(NeuralNetworkArchitecture<T> architecture, string modelPath, NeuralParametricEQOptions options) Creates a Neural Parametric EQ model in native training mode.

Properties

Property Summary
double EnhancementStrength { get; set; }
int LatencySamples { get; }
int NumChannels { get; }

Methods

Method Summary
ModelMetadata<T> GetModelMetadata()
Tensor<T> Enhance(Tensor<T> audio)
Tensor<T> EnhanceWithReference(Tensor<T> audio, Tensor<T> reference) Enhances audio by applying parametric EQ.
Tensor<T> ProcessChunk(Tensor<T> audioChunk)
void EstimateNoiseProfile(Tensor<T> noiseOnlyAudio)