How It Works

Audio Watermarking

Intrasonics audio watermarking is ideal in cases when there is direct access to the source audio or video that needs to be identified.  

Because the same piece of audio can be uniquely watermarked, it is possible to identify not just the content but also the context - e.g. the same TV advert running on different channels, or on the same channel at different times.

  1. Using Intrasonics software, extra sounds are hidden in audio and video content through an encoding process called Audio Watermarking.
  2. The Intrasonics decoder listens via a microphone and extracts data from the watermarks it hears.  Decoder SDKs are available for Android, iOS and Javascript.
  3. Your app, website or embedded hardware code is programmed to respond to watermarks in exciting and engaging ways. We provide some full examples in each SDK on which you can base your project.

FROM OUR TECH BLOG...
How does one watermark audio in such a way that it is robust to noise and distortions, but so that it won’t be noticed by a listener?

Audio Matching

Audio matching can be used without direct access to the audio or video media to match. For example, if the same TV advert airs on multiple channels then it will be identified as the same piece of content.  However, since the audio track is identical, differentiating between them is only possible using external data such as the known times of broadcast for the advertising.

  1. Using Intrasonics software, a recording of the audio or video to match is analysed and a "fingerprint" hash file is created.
  2. The Intrasonics SDK samples audio from a microphone and compares fingerprints it makes on-the-fly with those for known content. A set of fingerprints can be stored locally in the client device for faster matching and a huge database of fingerprints can be held on a server for broader matching.
  3. When a match is found, your app or website is programmed to respond in exciting and engaging ways. We provide some full examples in each SDK on which you can base your project.

FROM OUR TECH BLOG...
The human fingerprint for identification purposes is an extremely succesful data reduction method. Can we do something similar with audio, i.e. identify an audio track based on only a few key features?

Read our Tech Blog for more in-depth articles

Intrasonics Ltd

Bateman House
82-88 Hills Road
Cambridge
United Kingdom
CB2 1LQ

Get In Touch

+44 (0)1223 927 070
Make an enquiry