How to compare two audio files quality wise?
In order to compare two audio signals we introduce the analytical module, which compares separately combined pairs of fragments of active and inactive phase signal that allows getting more accurate estimation.
For each fragment we determine integral spectrum by using discrete cosine transformation (DCT). Spectrum integration is calculated according to the proprietary formula. In the spectrum calculation the interpenetration of windows comes to N/2 samples, and the Hamming or Blackmann-Harris window function is applied to every window. Levels of spectrum energy on bands are determined for all sets of bands. Groups of critical bands, determined by different authors resulting from different models of sound perception and speech production.
Band boundaries (initial and terminal indices) as well as band energy values we determine by a set of proprietary formulas. The initial quality estimation value is taken as 100%, which decreases proportionally to distinction of energies on bands. The most interesting fact is that we can scale down our percentage of signals similarity to the well-known Mean Opinion Score (MOS) values, which correspond in tests to Cisco MOS or ITU P.862 as precise as 97%. More interesting facts to follow – stay in touch!
