Talk:Perceptual Evaluation of Speech Quality

	Telecommunication portal This article is within the scope of WikiProject Telecommunications, a collaborative effort to improve the coverage of Telecommunications on Wikipedia. If you would like to participate, please visit the project page, where you can join the discussion and see a list of open tasks.TelecommunicationsWikipedia:WikiProject TelecommunicationsTemplate:WikiProject TelecommunicationsTelecommunications articles
Low	This article has been rated as Low-importance on the project's importance scale.

Hi,

PESQ is a well-recognized International standard for end-to-end voice quality assessment, however, there are several reasons why many companies are searching for alternative means to evaluate voice/speech quality in end-to-end testing. We would like to present an alternative approach that is capable of providing quality assessment in the same manner PESQ algorithm does and believe that it has a right to have its place on the PESQ related wiki discussion page. Thank you!

Please consider the presentation of this approach: http://sevana.biz/products/aqua/

194.105.208.40 (talk) 09:19, 16 June 2010 (UTC) Best Regards, Sevana Oy, Finland[reply]

Sevana presents unproven proprietary algorithm[edit]

How can Sevana Oy claim that their proprietary algorithm is by any means comparable with PESQ or its successor POLQA ? I have neither seen Sevana Oy participating in the PESQ competition nor in the recently completed selection phase for the the PESQ successor, namely Draft New ITU-T Recommendation P.863 (a.k.a P.OLQA). The testing efforts in the ITU-T competition where huge, with tens of thousands of speech sequences in the data bases.

There are dozends if not hundreds of non-standardized algorithms for all kind of voice quality estimation, prediction or whatever. It is easy to come up with such kind of algorithm, many people do that all the time. The real challenge here is to invest in thorough testing, benchmarking, characterization and so facing a strong competition under fair conditions under the umbrella of a Standards Developping Origanization.

I am holding leadership positions in ITU-T Stady Group 12 for more than two decades now, and it is pretty obvious that a proprietary unproved algorithm advocated by Sevana does by no means belong into the context of the PESQ Wiki. It is just a sad attempt of cheap advertisement.

One finds similar advertisement text in quite a couple of other fora, like the Nokia Discussion Forum, all placed by Sevana. It is simply spam and does not belong into the Wikipedia article on PESQ.

SG12 Expert (talk) 17:25, 16 June 2010 (UTC)[reply]

PESQ or POLQA? No, we selected Sevana AQuA[edit]

In case one needs to evaluate call quality intrusively and receive a reliable MOS score it really makes no sense to target at PESQ or POLQA. We are using Sevana AQuA for several years already both for NB and WB audio... — Preceding unsigned comment added by 91.215.122.93 (talk) 09:52, 14 March 2014 (UTC)[reply]