Voice Technology Trends in Conferencing Systems, Smart Whiteboards, and Interactive Kiosks
The ArkX Labs team recently attended the Audio and Video Expo in Mesa, Arizona. There were over 60 exhibitors covering a wide variety of applications, including conferencing video and audio systems, smart whiteboards, and interactive kiosks. There were also several non-traditional voice OEMs like medical device companies, robotics, and security device brands looking for voice solutions. We are always interested in understanding where OEMs and voice-enabled products are heading. Two things stood out at this conference as clear opportunities for our own EveryWordTM ultra far-field voice capture and control solutions.
Conferencing Audio Video Systems
Several exhibitors, such as Shure, Crestron, Clearone, Biamp, ATLONA, and Speech2data were showing in-room conferencing systems to address the current trend of hybrid and remote work scenarios. All the exhibitors emphasized their product’s high-quality video and audio capture, as well as their ease of deployment for the installers and ease of use for the end users. These systems use many built-in microphones (a few have up to 128 microphones) or rely on extension microphones throughout the room to perform voice capture with noise reduction and talker tracking. Such systems are complex to deploy and maintain. ArkX’s EveryWord Voice Technology uses only up to 4 integrated microphones to achieve clear 360° voice capture from up to 9 meters (easily accommodate a 12-seat conference room). This allows a conference system to be fully integrated and compact, which streamlines deployment, integration, ongoing management, and operation. EveryWord’s powerful noise reduction, echo cancellation, de-reverberation, and full-duplex controls all work seamlessly together to deliver highly intelligible, natural-sounding audio for a great conferencing experience.
This would be a significant improvement over the current OEM solution in the marketplace
Smart Whiteboards and Interactive Kiosks
T1V and ViewSonic showcased touch-screen displays and interactive software serving education, retail, collaboration, and kiosk applications. Currently, touch input is the primary user interface for smart whiteboards and interactive kiosks. Adding voice interactivity to touch is the next evolution in elevating true user convenience for these applications. These products are often deployed in loud environments like classrooms and retail spaces with high ambient noises. These products will need to manage ambient noises, which are detrimental to achieving optimal voice interface performance. These applications also operate in spaces with obstructions. ArkX’s EveryWord Voice Capture Technology can capture voice clearly in very noisy environments and around obstruction to enable highly accurate speech comprehension for Smart Whiteboards and Interactive Kiosks and also deliver highly intelligible voice communication with remote talkers when the situation demands.
Emerging Verticals
Our most fruitful discussions were with non-traditional companies exploring the use of voice capture and control for next-generation products. This included medical device companies, robotics, and security device brands. These companies saw real value in our far-field voice technology and its superior human-to-machine performance, especially EveryWord’s voice capture range and ability to work around obstructions and in loud or competitive noise environments with such accuracy. The status quo and performance of existing voice solutions are no longer ‘good enough.’
