AI restores women’s voice and overcomes speech disorders with technology: Health: Tech Times

This photo illustration shows a virtual friend on the screen of an iPhone on April 30, 2020 in Arlington, Virginia. (Photo: OLIVIER DOULIERY/AFP via Getty Images)

Alexis “Lexi” Bogan had a lively voice, which she was often heard singing along to her favorite songs or having lively conversations with friends. However, last summer her voice changed dramatically after doctors removed a life-threatening tumor from her brain.

Reclaiming Lexi’s voice

In August, surgeons successfully removed a life-threatening tumor from the back of her brain. After the breathing tube was removed a month later, Bogan developed difficulty swallowing and had difficulty speaking, struggling to convey a simple “hello” to her parents.

Despite months of dedicated rehabilitation, her speech remains limited, challenging her friends, family and even strangers in understanding her communication attempts. But Lexi transformed in April: she regained some semblance of her original voice.

However, it wasn’t her natural voice, but an artificial intelligence-generated replica accessed via a smartphone app. Based on a short recording from her teenage years, the AI ​​synthesized a remarkably authentic voice.

Using AI to restore speech

With just a few taps on her phone, the Associated Press reported that she can now command the app to express anything she wants, using her synthetic yet remarkably lifelike voice. The clip was originally from a cooking demonstration video for a school project.

Bogan, along with a group of medical professionals from the Lifespan hospital network in Rhode Island, are optimistic about a potential application that outweighs the potential risks.

Bogan represents one of the groundbreaking cases, and the only one with her specific condition, in which a lost voice has been successfully restored using OpenAI’s latest Voice Engine technology.

Her medical team deliberately provided the AI ​​system with a short 15-second recording for training. Despite some imperfections due to background noise during cooking, this short clip met OpenAI’s needs, a significant improvement over older methods that required longer recordings.

The doctors knew it was important to extract useful information from short recordings, especially for patients without digital voice tracks. These short recordings, like short voicemails, can be important for future reference.

Now she relies on the app about 40 times a day, providing feedback to potentially help future patients. One of her first efforts was speaking to the children at the kindergarten, where she serves as a teaching assistant.

She has used the app in stores to inquire about the locations of items. In addition, it facilitated reconnection with her father and simplified ordering fast food.

Bogan’s medical team has begun replicating the voices of other willing patients in Rhode Island, with ambitions to expand this technology to medical facilities around the world. OpenAI has made tentative progress in expanding the use of the Voice Engine, which has not yet been released to the public.

Also read: ElevenLabs AI Voice Generator can produce ’emotionally rich’ recordings in 30 languages

Dr. Rohaid Ali, a neurosurgery resident at Brown University Medical School and Rhode Island Hospital, expressed optimism about Lexi’s potential to facilitate future technological developments.

He highlighted the significant impact this innovation could have on millions of people affected by conditions such as stroke, throat cancer or neurogenerative diseases.

Related article: OpenAI is delaying the release of a voice cloning tool over concerns about misinformation

ⓒ 2024 All rights reserved. Do not reproduce without permission.