TimeStretch<T>
Models & Types · AiDotNet.Augmentation.Audio
Stretches or compresses audio in time without changing pitch.
Inheritance: AugmentationBase<T, Tensor<T>> → AudioAugmenterBase<T> → TimeStretch<T>
For Beginners
Time stretching makes audio faster or slower without changing the pitch - like how a slower speaker still has the same voice pitch. This is different from simply playing at a different speed.
How It Works
When to use:
- Speech recognition to handle different speaking speeds
- Music tempo adjustment
- Synchronizing audio with video
Constructors
| Constructor | Summary |
|---|---|
TimeStretch(double minRate, double maxRate, double probability, int sampleRate) |
Creates a new time stretch augmentation. |
Properties
| Property | Summary |
|---|---|
double MaxRate { get; } |
Gets the maximum time stretch factor. |
double MinRate { get; } |
Gets the minimum time stretch factor. |
Methods
| Method | Summary |
|---|---|
IDictionary<string, object> GetParameters() |