Main differences between POLQA and PESQ

1. Reference speech material: 48kHz vs. 8kHz sampling frequency
2.  MOS-LQO output: POLQA score directly represents estimated MOS values on a subjective scale of 1 to 5 MOS, unlike PESQ, which used the P.862.1 mapping function for conversion to the MOS domain
3.  Dual operational modes:
4.  Narrowband NB (IRS filtering up to 3.4kHz; 8kHz sampling frequency of the reference sample) For backwards compatibility to PESQ — recommended to berun only for this scope
5.  Super wideband SWB (Flat filtering up to 14kHz, 48kHz sampling frequencyof the reference sample)
6. Unique triple bandwidth output scale:
7.  SWB mode: NB, WB, and SWB tested samples presented on a single SWBscale (bandwidth being part of the transmission chain’s degradation)
8.  This has the advantage of direct comparison of different bandwidth scores. NOTE: It is generally expected that the SWB unique scale (running a SWB reference sample) has the following transparency:
1. • NB: Maximum MOS value 4.25
2. • WB: Maximum MOS value 4.5
3. • SWB: Maximum MOS value 4.75
9.  New extensively tested and validated languages: Chinese, Japanese, Czech
10.  Accuracy: POLQA proven to over-perform PESQ (both NB and WB)