Sevana Oy Blog » automatically

AQuA – Audio Quality Analyzer is now available for 64 bit servers!

admin — Mon, 15 Jun 2009 17:34:10 +0000

Hi,

Great news! Now AQuA (Sevana Audio QualityAnalyzer) is available under 32bit and 64bit operating systems!

- test voice and audio files quality

- compare two audio and voice files

- test voice codecs’ quality

- perform voice and audio quality measurement

Now this functionality is available both for Windows and Linux 64 bit and 32 bit systems. Voice quality testing software for Linux servers is provided on request.

How can I test this voice quality measurement software?

admin — Mon, 30 Mar 2009 19:09:20 +0000

Sorry for the pause with our new posts on voice quality! This temporary information gap will be over soon and meanwhile we would like to give an answer to such questions as:

- how can I compare two audio files to test voice quality?

- how can I test my codec for voice quality it provides?

The answer to the questions about is: please use contact information on these matters from here: http://www.sevana.fi/about.php

- is there a demo version I can play with?

Yes, it’s available for download from here: http://www.sevana.fi/audio_speech_codecs_quality_analysis.php

- demo version doesn’t allow comparing files! What can I do?

Please use contact information from here: http://www.sevana.fi/about.php and you may get a fully functioning software for your testing purposes!

- are there any updates to the functionality presented in the demo version?

Yes! There is a new version that actually tells you why there is a quality loss providing quantative feedback! And… you know where to go to inquire that version

Stay tuned!

Who’s the main competitor to the new method? What’s the catch?

admin — Mon, 02 Mar 2009 05:14:44 +0000

The solution we are talking about in these posts is DIFFERENT and gives added value to other products as it is not the so-called QoE (Quality of Experience) and does not rely on real-time user input, and it is neither based on MOS (Mean Opinion Score), nor operational parameters. The product in question IS different and covers a specific area, BEFORE any product is integrated and BEFORE one gets to the user experience and one can easily integrate it to a large system as a DLL library for instance. Or, if you have a system already operating you gain two big advantages: 1. generate a specch model to evaluate voice quality provided by your system and 2. test it on the fly by just simple audio files comparison.

It seems quite reasonable that the major competitor for the method is ITU P.862 – the so-called PESQ, but if you google it you will find out that there are just few World leaders that have this method implemented in their systems and… even fewer those who has actually done in-house as the majority would be using the same technology provider. (Just google it!)

Ok, what’s the catch? Price is one of them obviously and in order to get a better understanding on that please refer to this presentation (http://www.sevana.fi/Automatic_Sound_Signals_Quality_Estimation_Business_Benefits.pdf), but that’s not all. If one tries to compare PESQ and the method in question he would find out quite interesting differences and advantages in favor of the new method. But let’s leave it for the next post to digest the information better. See you reading our next post!

Is there a voice quality testing software that can compare two audio files? Does it have advantages if compared with existing ones? – Yes, this software already exists! Yes it does have advantages!

admin — Sun, 01 Mar 2009 06:28:24 +0000

All what we have described above has been implemented into a software tool and libraries that allow taking another sight to the problem of voice and audio quality measurement. The method of sound signal quality estimation has shown a number of advantages over known methods of quality evaluation:
-    it is universal since it allows judging the quality of signals from various source and processed in different ways;
-    one can optimize quality estimation signal depending on the purposes:
o    in speed (for example, it is possible to receive rough estimation quickly);
o    in signal type (using different bands for speech signals and sound signals in general);
-    resulting estimations correlate well (and sometimes even catches what the others don’t) with that of well-known stadards (МОS, PESQ);
-    quality estimations received for speech signals can be translated in values of various kinds of intelligibility.

To learn more about software test results, business benefits and integration possibililites please check this page http://www.sevana.fi/audio_speech_codecs_quality_analysis.php

We’ll get back to comparing the new method and providing more information about differences and advantages of it comparing to the other methods in the next post. Stay tuned!

Enough articulating – let’s calculate speech Intelligibility!

admin — Fri, 20 Feb 2009 04:35:04 +0000

Referring to the previous post concerning AI (Articulation Index) approach to voice quality measurement we would like to present another one: SII (Speech Intelligibility Index) which is the evolution of AI method. The American Standard ANSI S3.5-1997 includes the speech intelligibility index. It provides 4 measuring procedures on different band groups: 21 critical bands, 18 one third-octave bands, 17 equal by their contribution critical bands and 6 octave bands. The signal/noise ratio is calculated within every band and the total SII coefficient ranged from 0 to 1 is computed.

The speech intelligibility index takes into account only the properties of hearing, not speech production and that is an obvious disadvantage of the method..

More methods to automate voice quality analysis are about to follow in the next posts!