Skip to Content

What is SoundExpert

Audio metric that makes a differenceSoundExpert (SE) is an independent non-commercial audio research project, which provides audio quality ratings of sound equipment and technologies such as mp3, aac, wma ... encoders and portable players (to be extended). It is the home for innovative music-based audio metric which works both for objective audio measurements and for listening tests. SE is in beta state because the new audio metric and corresponding listening test design are not widely adopted by audio engineers. So, please, use our ratings with caution.

The new listener-centric audio metric allows to perform objective audio measurements using real-life music material and various technical signals, not only sine waves. Such measurements:
• correlate well to human perception of sound quality
• are valid for digital audio
• do not contradict traditional audio metric but extend it
• are understandable to people without technical background
• can be performed at home using any recording device

The first practical application of the new measurement method can be found on the Portable players page.

The new listening test design helps to hear sound artifacts which are normally beyond threshold of human perception. The core of the new design is sound artifacts amplification technology (SARTAMP), which is backed by the new audio metric. Such amplification is particularly important for testing high-bitrate encoders and high quality audio equipment. This technology is used in SE listening tests since 2005. The tests are blind - participants don't know the particular device they assess. Resulting quality scores are completely unbiased and free from marketing and advertising noise.

Live Listening Tests @SoundExpertThe ratings of encoders are computed in real time while participants of the listening tests send their grades to the rating system. The more participants - the more devices and technologies can be tested. The testing procedure is simple and short enough that anyone, including you, can participate. Just download a test file (<3Mb), listen it (<15s) and send back your grade. Details are in the test file. The more accurate grades - the more reliable ratings.

Detailed but still easy to understand overview of SE distributed listening tests is in the paper Live Listening Tests @SoundExpert.

* * *

The main idea behind SoundExpert project is consumer control over sound quality of various audio equipment and technologies on the market. Production side deserves clearly defined feedback from consumers.

 

 

Articles

« Back

TSAC - a neural network audio codec

TSAC - a neural network audio codec

Advances in neural network development have led to the emergence of a new class of audio encoders capable of packing audio data even more efficiently than psychoacoustic encoders. The secret to their success lies in the fact that neural codecs use not only knowledge about the characteristics of the human auditory system, but also knowledge about the structure of music and speech itself, their syntax or grammar. Neural networks acquire this additional knowledge through training on a large amount of musical and speech material. In terms of volume, this new knowledge surpasses psychoacoustic knowledge, which is why neural audio codecs require significantly greater computing resources to operate and are more cumbersome in themselves.

Their development is currently in its early stages, but many companies/developers have already presented working samples of neural audio codecs. A fairly complete list of developments can be found here - https://github.com/FORARTfe/HyMPS/blob/main/Audio/AI-based.md#codecs-

All of them exist in the form of source code and require some skill to try them out. However, there is one exception. Fabrice Bellard [https://bellard.org/] took the code from the Descript Audio Codec project as a basis, modified it for stereo signals, and compiled ready-made executable programs for Linux and Windows. This TSAC codec requires a GPU to work, but it also works on regular processors with AVX2 support, albeit slowly. The compression ratio is truly outstanding. With fairly acceptable quality, the average bitrate for 44/16/stereo material is about 7 kbit/s. For SE test samples, this bitrate turned out to be 6.37 kbit/s. This neural audio codec may not be the most perfect one at the moment, but it is available for testing by regular users and is therefore the first to be added to the listening tests on SE. An additional section, Encoders - 8 kbit/s, has been introduced for the purpose - https://soundexpert.org/encoders-8-kbps

More details about the codec can be found on its page - https://bellard.org/tsac/

As usual, anyone can participate in our listening tests. Feel free to try - https://soundexpert.org/testing-room

And as usual, it should be noted that since the testing is blind, you will not necessarily get the test file of this particular codec. After submitting your results, you will find out what you tested. Thank you in advance )!

Next
Comments
No comments yet. Be the first.
Audio-Transparency Initiative
Audio-Transparency Initiative