Your skin is your reflection. Anything about you, from your age to when you last fall sick can be known from your skin. Using that fact, an Israeli startup named VocalZoom wants your skin to do much more complicated analysis, understanding what you say.
Interferometer
The skin of our face makes exquisite vibrations while we talk. The amount of vibration is too low to be seen by human eye, but with an instrument called interferometer, VocalZoom team noticed it detect weird measurements.
“When it measures the face, we found out that the vibrations were caused only by the speaker’s voice and were not affected at all by any background voice,” said VocalZoom CEO Tal Bakish to Digital Trends. “At this point we realized that we have a disruptive technology to extract the voice of speaker in any noisy condition.”
The team built a sensor that can measure vibrations just by focusing on the speaker’s face from within a few feet, which are then translated into an acoustic signal. “This acoustic output is then fed into a typical speech enhancement or noise-reduction [program] to be fused with an acoustic microphone to create a practically noise-free signal that is fed to an automatic speech recognition [program],” said Bakish.
VocalZoom claims the resulted signal features very limited background noise, compared to those recorded by microphones and noise reduction units. Bakish hopes that signal may help match facial gesture with a speech to build more secure and accurate speech verification software.
“Over the past decade, solutions have relied only on data collected for training and strong processing technologies, such as neural networks and deep learning,” he said. “Now it is clear that to reach the 100 percent performance required for user adoption, the microphone technology needs to improve.”
The startup is currently in a partnership with Intel, Motorola Solutions, 3M, and some other companies. You can expect its technology featured in consumer devices as early as the next year. Also, they want to include the feature for voice control in vehicles and discussing it with some major car makers.
