Skip to main content
  1. Home
  2. Emerging Tech
  3. Health & Fitness
  4. News

A ’bionic’ larynx sounds far more natural than regular artificial voice boxes

Add as a preferred source on Google
New discovery to alter the path of Bionic Voice research worldwide

Scientists at the MARCS Institute at Western Sydney University in Australia have demonstrated a groundbreaking noninvasive artificial larynx that could be used to give a voice back to patients around the world, whose voice boxes have been removed as the result of cancer.

Recommended Videos

What makes the Pneumatic Artificial Larynx (PAL) demo different to other artificial larynxes is the fact that it doesn’t require invasive surgical implantation and utilizes a patient’s own respiratory system in order to work.

The existing type of treatment involving artificial larynxes means surgically implanting a prosthetic device into the stoma, an artificial opening in the neck made by a surgeon. Not only is this approach invasive, but it also opens patients up to the risk of infections and can result in a voice that sounds strained and whispery.

“Despite emergent progress in many fields of bionics, a functional Bionic Voice prosthesis for laryngectomy patients (larynx amputees) has not yet been achieved, leading to a lifetime of vocal disability for these patients,” the researchers write.

The so-called “Bionic Voice” offers an alternate approach. It is an electronic device that uses the patient’s own breath to create a humming sound. This is then converted into speech through the movement of the user’s lips and tongue. The result is an artificial voice box that can carry out the function of the larynx but without the degraded speech or associated health risks of other approaches. It’s an amazing advance that hints at enormous promise for the patients who may one day rely on this on a daily basis.

Next up, the researchers at Western Sydney University plan to develop the project in order to create a pneumatic bionic voice prosthesis that would take the form of a small “control unit” fixed over the patient’s neck, along with a “voice source” unit on the roof of a wearer’s mouth. This will reportedly improve speech levels further — resulting in more regular human-sounding speech far beyond the dreams of many people who previously used artificial larynxes.

A paper describing the work, titled “A pneumatic Bionic Voice prosthesis — Pre-clinical trials of controlling the voice onset and offset,” was recently published in the journal Plos One.

Luke Dormehl
I'm a UK-based tech writer covering Cool Tech at Digital Trends. I've also written for Fast Company, Wired, the Guardian…
Meta’s AI assistant finally lands on Mac, but it has some catching up to do
The new desktop assistant can analyze what's visible on screen and accept voice input across macOS.
Meta AI App on macOS Featured with logo

Meta has finally brought its Meta AI assistant to the Mac with a dedicated desktop app, giving users another AI chatbot to keep open alongside all those other tabs. The app can analyze a shared window, answer questions about what's on screen, generate content, and accept voice dictation across macOS.

Meta AI can actually see what's on screen

Read more
AI may be learning from billions of images without copying any one of them
MIT researchers have identified what they call “attribution decay” in large generative models.
Researchers generated an image using artwork from 744 artists, then compared it with outputs produced when each artist was individually removed from the training data

Here's an uncomfortable question for the generative AI era: if an AI creates an image, can anyone actually point to the specific images that influenced it? A new study from MIT's Computer Science and Artificial Intelligence Laboratory suggests that, for sufficiently large models, the answer may often be no. Researchers Dai and Gifford describe the phenomenon as “attribution decay” in their open-access paper, published today in Nature Communications. It refers to how the influence of any individual piece of training data becomes increasingly difficult to detect as the size of the dataset grows.

The bigger the dataset, the fuzzier the attribution

Read more
A boring tile wants to fix the worst problem of ultra-fast mmWave 5G connections for you
Researchers are using simple 3D-printed reflective surfaces to redirect mmWave signals around tricky indoor environments.
Wuqiong Zhao, UC San Diego PhD student and study co-author, holds a reflective tile.

5G's millimeter-wave technology can deliver incredibly fast wireless speeds, but it has an annoying weakness: those signals don't like getting around things. Walls, furniture, people, and even moving a few feet can cause mmWave connections to weaken dramatically. Now, researchers at the University of California San Diego are proposing a surprisingly boring solution: cheap reflective tiles that simply bounce the signal where it needs to go.

The problem with really fast 5G

Read more