NeuralFPOptions

Options & Configuration · AiDotNet.Audio.Fingerprinting

Configuration options for the Neural Audio Fingerprint (NeuralFP) model.

Inheritance: ModelOptions → NeuralFPOptions

For Beginners

NeuralFP creates “audio IDs” using AI instead of traditional signal processing. It converts a short audio clip into a small vector of numbers (like a barcode). Two recordings of the same song will produce very similar vectors, even if one is noisy or compressed. This enables Shazam-like audio identification.

How It Works

NeuralFP (Chang et al., 2021) uses a neural network to learn compact audio fingerprints for large-scale audio retrieval. It generates fixed-length embeddings from mel spectrograms that are robust to noise, compression, and time-stretching. The model uses contrastive learning to ensure similar audio produces similar fingerprints.

Constructors

Constructor Summary
NeuralFPOptions()

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 for training.
double MatchThreshold { get; set; } Gets or sets the cosine similarity threshold for considering a fingerprint match.
double SegmentDurationSec { get; set; } Gets or sets the segment duration in seconds for fingerprint extraction.
double Temperature { get; set; } Gets or sets the temperature for contrastive loss during training.
int BaseFilters { get; set; } Gets or sets the base filter count for convolutional layers.
int EmbeddingDim { get; set; } Gets or sets the fingerprint embedding dimension.
int FftSize { get; set; } Gets or sets the FFT window size in samples.
int HopLength { get; set; } Gets or sets the hop length between frames in samples.
int NumConvBlocks { get; set; } Gets or sets the number of convolutional blocks in the encoder.
int NumMels { get; set; } Gets or sets the number of mel filterbank channels.
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.