By default, the "SpectralEuclidean" distance is used:

Various distances are computed on the sample values of the audio signals:

Distances computed on the spectrum compare the frequency content rather than the sample values:

Phase differences of the signals do not affect the computed spectral distance:

By default, any distance measure uses the most suitable audio feature:

Most distances use "AudioData" as the default feature:

With WarpingDistance, the "MFCC" feature is used by default:

Specify a different feature:

All features other than "AudioData" are computed from the signal's short-time Fourier transform:

If two signals have different lengths, the longer is trimmed to the shorter duration:

To compare the full length of the signals, use Masking->All:

Use the Masking option to compare a specific interval of two audio objects:

As long as the duration of the intervals is the same, they can be chosen from different times:

Use MaskingAll to compare the full length of the signals:

Use the PartitionGranularity option to control the computation of the features:

If the selected feature is "AudioData", the PartitionGranularity option is ignored:

By default, all audio signals are converted to the higher sample rate:

Use a specific sample rate: