Over a million developers have joined DZone.
{{announcement.body}}
{{announcement.title}}

New Algorithm Promises to Make Hearing Better

DZone's Guide to

New Algorithm Promises to Make Hearing Better

Who doesn't want to be far from the maddening crowd? Well there might be an app (or at least an algorithm) for the sonic equivalent of that.

· Big Data Zone ·
Free Resource

Hortonworks Sandbox for HDP and HDF is your chance to get started on learning, developing, testing and trying out new features. Each download comes preconfigured with interactive tutorials, sample data and developments from the Apache community.

Businessman Irritated with Loud Coworker

A while back I wrote about some research that suggested that a bit of background noise can be great when we’re trying to innovate.  Whilst that may well be true, background noise is a major pain in the behind for those equipped with a hearing aid.

Thankfully, a team of researchers from New York University have managed to develop an algorithm that can filter out that hubbub and help the hard of hearing decipher what’s really important.

Algorithmic Hearing

They’ve developed an algorithm that is able of detecting the talker’s voice, and can thus distinguish that from less important noise.  The approach is interesting because most existing methods are ok at eliminating steady background noise (such as your air con) but struggle with noise that is similar to the foreground noise you hope to capture, such as the babble in a coffee shop.

To manage this, the team developed a noise reduction technology, called SEDA (for Speech Enhancement using Decomposition Approach), which breaks the speech into waveforms that allow differentiation on both frequency and number of oscillations.

“Some waveforms in the SEDA process comprise many oscillations while other comprise just one,” the team say.“Waveforms with few oscillations are less sensitive to babble, and SEDA is based on this underlying principle.”

This approach is only viable today because computational power has developed to such an extent as to make it effective and efficient.  The progress made however promises to make a huge difference to the life of a hearing impaired individual, although the technology is still some way from becoming ready for consumers, and it’s still unclear just how expensive it will be.

Suffice to say, the technology may also have applications for those with better hearing.  For instance, if you’re trying to use your phone in a noisy environment it might be able to shut out the background noise for you.

It’s a fascinating technology and it will be interesting to see how it develops.

Hortonworks Community Connection (HCC) is an online collaboration destination for developers, DevOps, customers and partners to get answers to questions, collaborate on technical articles and share code examples from GitHub.  Join the discussion.

Topics:
audio processing ,noise ,speech recognition

Published at DZone with permission of

Opinions expressed by DZone contributors are their own.

{{ parent.title || parent.header.title}}

{{ parent.tldr }}

{{ parent.urlSource.name }}