Cambridge-based audio-software specialist AudioTelligence has developed new technology aimed at solving the ‘cocktail party problem’, whereby hearing aid users find it difficult to follow a conversation taking place in a noisy environment.
According to the company, its Aiso for Hearing technology improves speech understanding in noisy environments from five per cent to 98 per cent, a significant improvement over existing commercially available devices.
Current assistive-listening technologies, based on beamforming and noise suppression, provide only a partial solution to the problem. Aiso for Hearing adopts a different approach. Rather than simply amplifying all sounds from a particular direction, Aiso separates the speech signals from the surrounding noise, allowing users to hear individual voices clearly.The technology improves the speech-to-noise ratio by up to 30 decibels – compared with improvements of only two to four decibels for the directive beamformers typically found in hearing aids.
Aiso for Hearing is a software solution that employs a combination of blind-source separation and noise suppression, first analysing the acoustic scene, separating sound sources and isolating the voices of interest, and then using noise-suppression techniques to reduce the background noise. The technology has a latency of only five milliseconds, which is crucial for assistive-listening solutions because they need to work in real time to avoid ‘lip sync’ issues.
AudioTelligence has incorporated the technology in a prototype tabletop device, pictured above, that is compatible with smart phones and existing hearing solutions.
‘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.’
According to research carried out by the company, some 80 per cent of adults aged between 40 and 64 find it difficult to follow conversations in noisy environments, suggesting that more than 200 million people worldwide could be helped by the new device.
‘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,’ Roberts continued. ‘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.’