Yokneam Illit, Israel and Hefei, Anhui, China --- VocalZoom, supplier of Human-to-Machine Communication (HMC) optical sensors, has signed an agreement with iFLYTEK to combine and test the performance of VocalZoom’s optical HMC sensor with iFLYTEK’s Voice Cloud intelligent speech technology platform. Initial results show that the ASR performance of iFLYTEK’s platform can be improved an average of 50 percent, and even more in noisy environments, by adding VocalZoom sensors to user headsets and automotive infotainment solutions.
The key for human-to-machine interactions using virtual assistants and automotive voice control is whether the machine did what it was told, quickly and accurately enough to satisfy the user. Even with the latest noise reduction algorithms, today’s acoustic microphones can’t achieve adequate voice isolation for this level of control, especially in noisy environments. The VocalZoom multifunction HMC sensor overcomes this problem by gathering additional data generated during speech as facial skin vibrates around the mouth, lips, cheeks and throat. By integrating the VocalZoom optical HMC sensor into a voice-control solution and focusing it on these areas, facial vibrations can be acquired, measured and converted to an isolated, near-perfect reference signal with which the system can operate – regardless of noise levels.
VocalZoom and iFLYTEK have tested the performance of a solution combining both companies’ technologies inside a moving automobile across a number of scenarios with varying levels and combinations of music, car noise and other interference. ASR performance is improved to an almost perfect score in environments where high noise previously made adequate voice-control performance impossible.