Human speech recognition may be improved by machine learning as per a study at the American Institute of Physics, published in The Journal of the Acoustical Society of America, by the Acoustical Society of America through AIP Publishing.

Hearing loss is among the rapidly increasing disability among many babies as they age. To overcome the impact of hearing loss, researchers often use hearing aid algorithms for improving human speech recognition. The present study utilized a combination of machine learning and deep neural networks.

“The novelty of our model is that it provides good predictions for hearing-impaired listeners for noise types with very different complexity and shows both low errors and high correlations with the measured data. We were most surprised that the predictions worked well for all noise types. We expected the model to have problems when using a single competing talker. However, that was not the case,” says author Jana Robach, from Carl Von Ossietzky University.