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)

The move from PESQ to POLQA is recommended (and will eventually be
required) due to:

 POLQA fixes well-known weaknesses of PESQ
 POLQA copes with today’s speech codecs, voice enhancement devices,
and network conditions
 POLQA offers significantly higher accuracy


POLQA technology has still some limitations that must be well understood and
controlled

Main differences between POLQA and PESQ:

 Reference speech sampling frequency
 Operational modes / bandwidths
 Unique triple bandwidth MOS LQO output scale
 Accuracy

Reason 1. POLQA fixes known and recognized PESQ weaknesses.

1. WB measurements in general
2. Inaccuracy with CDMA codecs (e.g., EVRC) and, therefore,
3. CDMA networks in general
4. Sensitivity to certain GSM/WCDMA network conditions
5. (DTX/Voice Activity Detection in AMR codec)
6. VoIP limitations (variable delay up to 1sec)
7. Strong linear distortions (e.g., phone’s frequency shaping) as well as gain variations
8. Limitations with speech processing (enhancement) devices
9. (noise reduction, automatic gain control)

Reason 2. POLQA has new operational features.

 Works in all three available bandwidths (NB, WB, SWB) and under different

background noise conditions (street, car, restaurant, babble, impulse, etc.)

 Works with all new commercial and standardized codecs used in different

technologies (GSM/WCDMA, LTE, VoIP, VoIP over IMS) such as

AMR-WB, EVRC-WB, iLBC, AMB+, AAC, Skype / SLIK, G.711, G.729, etc.

 Allows measurements at various combinations of interfaces:

electrical-electrical, acoustical-acoustical, electrical-acoustical, and

acoustical-electrical — providing the opportunity to test terminals and

hands-free applications