WAVE SCIENCES Acoustical Focus
Does your team need to extract and clarify speech or other audio?
WAVE SCIENCES Acoustical Focus™ is a user-friendly software application for speech enhancement, audio forensics, and acoustic analysis that enables you to extract and clarify targeted sources in any multichannel recording.
It uses the groundbreaking GLIMPSE™ engine to isolate a specific targeted source (e.g., a desired speaker or conversation) and suppress extraneous masking sources (e.g., competing conversations) so that you can easily understand the desired source.
The groundbreaking GLIMPSE™ engine became the first general solution to the Cocktail Party Problem by being able to selectively refocus an incoming soundfield on an audio source to clarify it. At the same time, it blurs out all other sources, including competing talkers and noises, in an manner similar to refocusing a blurry photograph or using portrait mode on a camera to create a depth of field effect.
When compared to human hearing, it is mimicking the brain's Spatial Release from Masking effect. Because of this mimicry, it may also provide intriguing insights into human spatial hearing and even serve as a viable computational model of what is going on in the brain.
The GLIMPSE engine uses machine learning (popularly known as a form of artificial intelligence, or AI) to deliver results that are an order of magnitude superior to any competing approach, even under uncontrolled, real-world conditions.
GLIMPSE does not require special sensors or prior knowledge of the sensor arrangement. It mathematically learns the physical 3D acoustical space in relation to the microphones from clues in the multichannel recording, again mimicking a feature of human hearing.
GLIMPSE demonstrated some of its power to the wider world with its judicial debut in 2022, when it was deemed instrumental in a conviction obtained by the State of Florida for the Dan Markel murder. In that case, the US State Circuit court admitted the full 41 minutes of audio evidence enhanced with GLIMPSE. In the previous trial, before GLIMPSE, the court would admit only 15 seconds due to lack of intelligibility.
Beyond the forensic applications, other potential uses for Acoustical Focus and GLIMPSE include:
Conferencing Systems
The industry assumption is that even in well-conducted meetings there is around 15% overlap of speech, which causes errors in automatic speaker diarization and recognition engines.
Hearing Assistance
Individuals with hearing loss frequently cannot distinguish individual voices or other sounds in the presence of man-made noise, competing speech, and reverberation. Existing hearing assistive technologies are ineffective beyond about an arm's length away in places like restaurants, cafes, train stations, and airplanes.
Voice USer Interfaces
Our machine learning spatial audio technology can exploit a voice user interface's “wake word” to focus on the talker giving the command, even from the back seat of an automobile or across a room, focusing past other voices and noise in between. Asking everyone else to be quiet while interacting with a voice assistant is no longer necessary, which may propel the use of voice assistants into new areas, such as factory floors, airplanes, and "big box" retail stores.
Government
Government agencies around the world rely on Wave Sciences' technologies in forensic, communications, search & rescue, first responder, officer safety, hostage rescue, VIP protection, detention centers, and other applications.
For details, please contact us.