The following diagram shows the modules in IDOL Speech Server that create audio fingerprints in a single step.
|
The a is the audio window series.
The fp is the feature vector series.
The tr is the recognized track labels and time positions.
The |
The schema that implements this feature is:
[MyAfpMatch] a ← wav (MONO, input) fp ← afpfeature (_, a) tr ← afp (_, fp) output ← afpout (_, tr)
|