FRCRNOptions

Options & Configuration · AiDotNet.Audio.Enhancement

Configuration options for the FRCRN (Frequency Recurrence CRN) model.

Inheritance: ModelOptions → FRCRNOptions

For Beginners

FRCRN uses a clever trick: it processes audio frequencies in sequence (low to high) like reading a book, so each frequency knows about its neighbors. This helps it distinguish speech from noise because speech frequencies are correlated (they appear together), while noise frequencies are more random.

How It Works

FRCRN (Zhao et al., ICASSP 2022, Alibaba DAMO Academy) uses frequency recurrence to model spectral correlations and complex spectral mapping. It won 1st place in the ICASSP 2022 DNS Challenge non-personalized track with superior noise suppression while preserving speech quality.

Constructors

Constructor Summary
FRCRNOptions()

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 EncoderChannels { get; set; } Gets or sets the encoder channel dimension.
int FFTSize { get; set; } Gets or sets the FFT size.
int HopLength { get; set; } Gets or sets the hop length.
int LstmHiddenSize { get; set; } Gets or sets the LSTM hidden size for frequency recurrence.
int NumFreqBins { get; set; } Gets or sets the number of frequency bins.
int NumStages { get; set; } Gets or sets the number of encoder-decoder stages.
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 (“base” or “large”).