Deep clustering machine learning enables AI to distinguish individual voices in a crowd
AI system can isolate individuals’ voices from other environmental noise, including other voices. Such a system has many potential uses, both benign and nefarious. The ability is rapidly improving to untangle signals from noise and identify which signals are from which sources. The approach should be able to apply to other kinds of signals too, not only sounds.
https://www.newscientist.com/article/2151268-an-ai-has-learned-how-to-pick-a-single-voice-out-of-a-crowd/
Perhaps an AI-enabled solution can be devised for hidden hearing loss (HHL), an auditory deficit in which a person does well on the typical tone-recognition hearing tests, but has difficulty understanding another person’s speech in environments where many people are speaking in the background or there are other background noises. HHL is attributed to synaptic disruption in the auditory nerves, rather than to loss of cilia in the ear canal. Nerve demyelination may also contribute. I foresee a new type of hearing aid that uses AI-enabled signal separation and clarification to help people with HHL. Early versions might require the… Read more »