Living with a Hearing Aid

A blog covering how to engage fully with life and the people you care about

What is DNN? 5 easy steps for understanding DNN and its benefits

Reading Time: 2,5 min.
16/12/20

5 easy steps for understanding Oticon More™’s new technology and its benefits

Oticon has launched a new hearing aid, Oticon More™. Inside this new hearing device there is a deep neural network, or DNN, which will help to give you an even better listening experience. But what is a DNN and how could it help you to hear?

 

It sounds complicated, but let us try to explain.

DNN is a type of machine learning that mimics the way the brain learns. It’s been used for a variety of tasks; some that you might be familiar with, like language translation and image search tools, and some that you might not know about, like medical diagnosis – UCLA trained a DNN to detect cancer cells!1 Now, we’re using it for our new hearing device, Oticon More.

The general idea of a DNN is that it learns through repetitive action from a collection of samples, like 100 pictures of different dogs, as opposed to a set of man-made rules, like “a dog has a black nose and floppy ears.” In this way, a DNN learns in the same way the human brain does – through practice and making mistakes.

Here’s how it works:

  1. A computer is given a piece of information, like an image or a sound. Let’s say in this example it’s given a trumpet sound. Unlike you or I, a computer wouldn’t know what this is.

  2. The computer passes this sound through its DNN, recognizing what it can and sorting elements of it – like a high pitch or a low pitch sound.

  3. When it reaches the end of this process it decides if the sound is a trumpet or not.

  4. It’s given feedback on this answer – a yes or a no – which the computer uses to strengthen its decision making

  5. The process is repeated over and over with lots of different trumpet sounds, until the computer can learn to recognize it instantly. Just like a brain would.

Now let’s say this DNN was trained with millions of real-life sound scenes – a restaurant, train station or busy street. The DNN would learn to identify and balance each sound within it, so you can access the sounds most important to you.

So that’s exactly what we did! We trained a DNN with 12 million complex real-life sound scenes like these, which it then learned to analyze, organize and balance. After it had learned all this awesome knowledge, it was ready to power Oticon More. Now this hearing device can utilize the DNN’s intelligent capabilities when balancing and prioritizing the sounds that are important to you, which also supports your brain health.

 

 

The benefits of having a hearing aid with DNN

Imagine you are in a restaurant with friends or family. The person in front of you is talking as you stand to leave. Because a traditional hearing aid is trained to focus on speech directionality and cancel all other noise – especially in loud environments – you might not hear the waiter stood behind you with a tray full of glasses.

With DNN, your brain has access to the full sound scene, so you could hear the person next to you, the clatter of cutlery on a plate a table over and the waiter stood behind you – all balanced and amplified in a true-to-life way.

This is because a DNN provides your brain with more meaningful sound information, which makes sound much clearer and speech easier to follow. In fact, our research shows that the full sound scene is 60% clearer2 when using the DNN in Oticon More.

See what our test group had to say about Oticon More

 

 

From rediscovering forgotten sounds to no longer being held back by noisy situations, Oticon More’s revolutionary use of DNN could have a great impact on your life.

Find out more about Oticon More here.

If you’d like to learn more about DNN, read our technology page.

 

_________________________________________

[1] Bahram Jalali, Claire Lifan Chen, and Ata Mahjoubfar, University of California, Los Angeles (UCLA)

www.mathworks.com/company/newsletters/articles/cancer-diagnostics-with-deep-learning-and-photonic-time-stretch.html

[2] Santurette, S., Juul Jensen, J., Ng, E.H.N. , Man, K.L.B (2020) Oticon More(TM) Clinical Evidence. Oticon Whitepaper