MPSENetOptions

Options & Configuration · AiDotNet.Audio.Enhancement

Configuration options for the MP-SENet (Multi-Path Speech Enhancement Network) model.

Inheritance: ModelOptions → MPSENetOptions

For Beginners

Sound has two components: loudness (magnitude) and timing (phase). Most enhancers only fix loudness and leave timing alone, which limits quality. MP-SENet fixes both simultaneously using two parallel paths that share information, leading to cleaner and more natural-sounding audio.

How It Works

MP-SENet (Lu et al., 2023) predicts both magnitude and phase of the complex spectrogram using parallel magnitude and phase estimation paths with a cross-domain fusion module. It achieves PESQ 3.60 on VoiceBank+DEMAND, surpassing prior single-channel methods.

Constructors

Constructor Summary
MPSENetOptions()

Properties

Property Summary
OnnxModelOptions OnnxOptions { get; set; } Gets or sets the ONNX runtime options.
double DropoutRate { get; set; } Gets or sets the dropout rate.
double LearningRate { get; set; } Gets or sets the learning rate.
int FFTSize { get; set; } Gets or sets the FFT size for STFT computation.
int FeedForwardDim { get; set; } Gets or sets the feed-forward dimension.
int HiddenDim { get; set; } Gets or sets the encoder hidden dimension.
int HopLength { get; set; } Gets or sets the hop length for STFT computation.
int NumAttentionHeads { get; set; } Gets or sets the number of attention heads.
int NumFreqBins { get; set; } Gets or sets the number of frequency bins (FFTSize / 2 + 1).
int NumLayers { get; set; } Gets or sets the number of encoder layers.
int SampleRate { get; set; } Gets or sets the expected audio sample rate in Hz.
string ModelPath { get; set; } Gets or sets the path to the ONNX model file.
string Variant { get; set; } Gets or sets the model variant (“small” or “large”).