All durations, spans and spacings are given in sample frames with respect to the sample rate of the audio input file.
The result is a sequence of matches, sorted by descending similarity
The result is a sequence of matches, sorted by descending similarity
where temporal weight is between 0 (just spectral corr) and 1 (just temporal corr)
A processor which searches through the database and matches entries against a given audio file input. Returns a given number of best matches.