People with hearing loss often experience that they have difficulties understanding speech in noisy situations with background noise. The phenomenon is known as ”the cocktail party effect”. Researchers at The Ohio State University in the US may have solved this problem.
- Focussing on what one person is saying and ignoring the rest is something that normal hearing listeners are very good at, and hearing impaired listeners are very bad at, but we have come up with a way to do the job for them, says Eric Healy, professor of speech and hearing science and director of Ohio State Speech Psychoacoustics Laboratory in the US.
The solution is a computer algorithm that quickly analyses speech and removes most of the background noise.
Removed background noise
In the tests, Healy and his team removed twelve hearing-impaired volunteers’ hearing aids, then played recordings of speech obscured by background noise over headphones. They asked the participants to repeat the words they heard. They then re-performed the same test, after processing the recordings with the algorithm to remove background noise.
They tested the algorithm’s effectiveness against ”stationary noise” — a constant noise like the hum of an air conditioner and then with the babble of other voices in the background.
The algorithm was particularly effective against background babble, improving hearing-impaired people’s comprehension from 25% to close to 85% on average. Against stationary noise, the algorithm improved comprehension from an average of 35% to 85%.
For comparison, the researchers repeated the test with twelve undergraduate students who were not hearing impaired. They found that the scores for the normal-hearing listeners without the aid of the algorithm’s processing were lower than those for the hearing-impaired listeners with processing.
That means that hearing-impaired people who had the benefit of the algorithm could hear better than students with no hearing loss, Healy said.
The initial tests focused on pre-recorded sounds. In the future, the researchers will refine the algorithm to make it better able to process speech in real time.
The technology may be used in the future generations of digital hearing aids.
The findings have been presented in ”Journal of the Acoustical Society of America”.