Article By: Dr David Groesch, Central Illinois Hearing
Like it or not Artificial Intelligence (AI) is here to stay. It has the capability of taking your pizza order to solving complex medial conditions or solving one of the most vexing problems affecting people with hearing loss.
Understanding Speech
The human brain is the most powerful processor, naturally good at filtering sounds in noisy environments, so people can instinctively tune in to what they want to hear. When challenged with hearing loss, the brain does not receive the right input to take advantage of this natural ability. This is why hearing aids are increasingly employing AI to provide extra help with hearing noise when needed, so the brain can do what it is naturally good at, preserving natural hearing processing.
The concept of Ai in hearing aids is too vast even for this author to fully explain but I’ll try. Ai is best explained as an algorithm with brain-like logical structures called Deep Neural Networks capable of making decisions after being after being trained with vast amounts of data. To train a DNN, the algorithm is shown many pairs of inputs and labeled outputs. The algorithm then must “learn” for itself what rules can be used to arrive at the correct output for any given input through repeated attempts and continuous feedback about those attempts. It uses information from the past to make more accurate and faster predictions. By having a large dataset with plenty of variability, the DNN will be able to generalize in other words, to handle data it has never seen in training.
Are you still with me? Not too complicated, right?
Here’s an analogy, if a data set contained 10 pictures of horses, the DNN might correctly identify a new picture of a horse 5% of the time. The other 95% of the time it might think it is looking at a dog or a table. If the training set contained 10,000 pictures of a horse, then the DNN is likely to identify a new picture of a horse almost 100% of the time. So, like the human brain the more a hearing aid receives similar sounds, it will learn to identify those sounds as “important” sounds and will be better able to recognize patterns and make decisions. Ultimately what the human brain does with this sound depends on the severity of ones hearing loss, but for most hearing-impaired people it’s a vast improvement.
AI development in hearing aids technology is just emerging, and I can’t think of anything where AI holds more promise than in hearing aids. If this blows our mind, did you know that some hearing aids can monitor your heart rate, amount of daily exercise and fall detection? Welcome to life in the 21st century!