Video: Hearing tech improves speech understanding in noisy environments by 98 percent

“Breakthrough” assistive listening technology is set to improve speech understanding in noisy environments by addressing the ‘Cocktail Party Problem’ and facilitating seamless conversation following.

Audio software specialist AudioTelligence has announced its new aiso for Hearing product, which the firm says has been demonstrated to improve speech understanding in noisy environments from five percent to 98 percent, representing a “significant” improvement over existing available devices.

The software works by separating the speech signals from the surrounding noise. This allows a user to hear individual voices clearly, with the technology giving an improvement in the speech-to-noise ratio (SNR) of up to 30 decibels (dBs). This is compared with improvements ranging between 2-4 dB for the directive beamformers typically found in hearing aids, according to the firm.

The technology can be integrated into multi-microphone devices – including smartphones and hearing solution products – to give them enhanced assistive listening capabilities.

AudioTelligence says the software works differently to current assistive listening devices, which typically amplify all sounds from a particular direction. It means that when typical hearing aids are used in noisy environments, they tend to amplify the background noise as well as speech, so users can still find it difficult to follow the conversation. According to the company, current technologies only provide a partial solution to the ‘Cocktail Party Problem’.

Now, its latest aiso for Hearing product is set to help more than 200 million globally looking for a solution that helps them follow conversations in noisy situations, as found in AudioTelligence’s research.

“Our alternative very low latency approach separates voices from noise, improving speech intelligibility, whereas other solutions tend to just amplify sound from a particular direction,” said Ken Roberts, CEO of AudioTelligence. “At the same time, aiso for Hearing suppresses background noise, minimising the effort needed to follow a conversation and reducing listening fatigue. And if there are multiple conversations happening around them, the user can pick which one they wish to focus on, eliminating the unwanted speech.

“Our technology portfolio is the result of more than 12 years of research into the most effective approaches for extracting clean speech signals in complex acoustic scenes. This has enabled us to develop assistive audio technology to solve the cocktail party problem and help 200 million people worldwide to join the conversation.”

aiso for Hearing uses a combination of patented blind source separation and noise suppression for a two-pronged approach to the cocktail party problem.

The technology first analyses the acoustic scene, separating sound sources and isolating the voices of interest. It then uses noise suppression techniques to reduce the background noise.

As well as following conversations easily in the automatic mode, there is also a focus mode. The focus mode enables the user to focus on a particular speaker when there are multiple conversations taking place. This feature can be used on video calls, recordings, or in real-time environments.

AudioTelligence’s expertise in blind source separation from multi-microphone devices has enabled the company to develop both technologies with the very low latency (5 ms). Low latency is crucial for assistive listening solutions, the firm underlines, which need to work in real time and which must avoid ‘lip sync’ issues.

AudioTelligence has produced a prototype tabletop device to showcase the new assistive technology.

Watch the video below for a demonstration of the technology action in action: