IGenreClassifier<T>

Interfaces · AiDotNet.Interfaces

Interface for music genre classification models.

Implements: IFeatureAware, IFullModel<T, Tensor<T>, Tensor<T>>, IGradientComputable<T, Tensor<T>, Tensor<T>>

Known implementations: GenreClassifier<T>

For Beginners

Genre classification is like having an expert listener label what type of music a song is.

How it works:

  1. Audio features are extracted (mel-spectrograms, MFCCs, etc.)
  2. A neural network analyzes these features
  3. The network outputs probabilities for each genre

Common genres:

  • Rock, Pop, Hip-Hop, R&B
  • Jazz, Blues, Classical
  • Electronic, EDM, House, Techno
  • Country, Folk, Reggae

Use cases:

  • Music library organization
  • Streaming service recommendations
  • Radio station automation
  • Music analysis and research

Challenges:

  • Genre boundaries are fuzzy (many songs blend genres)
  • Genre definitions vary between cultures and time periods
  • Sub-genres vs main genres (is “death metal” a genre or sub-genre?)

How It Works

Genre classification automatically categorizes music into genres like rock, jazz, classical, hip-hop, etc. This is useful for music organization, recommendation, and discovery.

This interface extends IFullModel for Tensor-based audio processing.

Properties

Property Summary
IReadOnlyList<string> SupportedGenres { get; } Gets the list of genres this model can classify.
bool IsOnnxMode { get; } Gets whether this model is running in ONNX inference mode.
bool SupportsMultiLabel { get; } Gets whether this model supports multi-label classification.
int SampleRate { get; } Gets the expected sample rate for input audio.

Methods

Method Summary
GenreClassificationResult<T> Classify(Tensor<T> audio) Classifies the genre of audio.
GenreTrackingResult<T> TrackGenreOverTime(Tensor<T> audio, double segmentDuration) Tracks genre over time within a piece.
IReadOnlyDictionary<string, T> GetGenreProbabilities(Tensor<T> audio) Gets genre probabilities for all supported genres.
IReadOnlyList<GenrePrediction<T>> GetTopGenres(Tensor<T> audio, int k) Gets top-K genre predictions.
Task<GenreClassificationResult<T>> ClassifyAsync(Tensor<T> audio, CancellationToken cancellationToken) Classifies genre asynchronously.
Tensor<T> ExtractFeatures(Tensor<T> audio) Extracts audio features used for classification.