Voice-Enabled Applications in Public or Loud Work Spaces
According to Market Research Future, the global far-field speech and voice recognition market will triple in the next five years, dominated by in-home voice assistants and speaker bars like Google and Amazon’s Alexa. But there are emerging opportunities that are increasing outside the home. Think public and workspaces like commercial buildings, retail, hospitals, airports, classrooms, hotels, industrial sites and manufacturing facilities. In fact, the evolution of voice is well underway as OEMs look to increase productivity and improve customers’ experiences. These diverse environments have several elements in common: they are loud, reverberative, and filled with multiple competing noise sources. The existing and most popular OEM voice solutions cannot deliver the clear and accurate level of human-to-machine speech recognition required to operate effectively in these challenging spaces. “Good enough” is no longer good enough. Engineers are looking for a better way forward.
Enabling Premium Performance for Voice-Directed Applications
Our EveryWordTM Ultra Far-Field Voice Capture technology, featuring Cirrus Logic, NXP, and Sensory technologies, was designed to deliver superior hands-free performance up to 3X the distance (up to 9 meters) of competitors’ solutions, and around corners, while reducing competing noise sources and permitting reliable barge-in capability. Along with the ability to integrate custom wake-words and command sets for a branded workplace voice experience, EveryWord’s advanced audio front end (AFE) technology is well-suited for a wide range of voice-enabled applications being developed to operate in these challenging spaces, including:
- Smart factory and warehouse assistants for robotics, data access, manufacturing lines, and control computers
- Voice-directed medical and patient-care devices in healthcare facilities
- Touchless kiosks in commercial lobbies, retail, airports, public transportation stations, and more
- Drive-through transactions and bank ATMs
- Voice-enabled smart tools and equipment for construction or industrial worksites
- Agricultural machinery and cab-function control
- Touchless elevator control for buildings
- Hotel rooms and check-in kiosks, conference and classroom rooms, , self-check-out grocery stores, gyms, etc.
Once people begin to operate smart tools, vending machines, and elevators using just their voices without ever having to touch any buttons or screens, there will be no going back.
So What’s the ‘Secret Sauce’?
EveryWord™ ultra far-field technology is based on 3-D reverberation science. This 3-D reverberation doesn’t rely on geometric constraints to define microphone configuration, placement, or orientation. The old beamforming technologies often resulted in false positives and false negatives or required users to repeatedly shout to have devices hear them accurately. 3-D reverberation overcomes those problems.
In addition, our technology tolerates fixed and moving obstructions in the audio path, making it perfectly suitable for a wide variety of public and workspaces where there there might be building features, machinery or even other people in the audio path between the talker and the microphones.
Another game-changer is the use of 12 independent Acoustic Echo Cancellers (versus the competition’s standard one or two) that provide superior barge-in performance.
Finally, ArkX offers platform-neutral solutions. The ArkX solution is simultaneously compatible with multiple voice services and trigger-word
providers, including Alexa, Google, Siri, Cortana, AliGenie, Baidu/Kitt.ai, Tencent, and our collaboration with Sensory. This allows the user to pick and choose from the best of available skills from each platform and craft a solution that suits his or her specific needs.
OEMs are Taking Notice
From an OEM’s perspective, the real limitations with the current built-in options that dominate the voice space are overcome with our technology. There is a growing number of companies across a wide variety of verticals that want a much higher standard of performance, something that can be customized to work seamlessly within their eco-systems, for their customers or employees. With the acceleration of far-field voice technologies like EveryWord, and the emergence of Artificial Intelligence (AI) and machine learning, many OEMs are already driving innovation in applications that go way beyond the home space. The opportunities are endless.