VocalZoom Partners with iFLYTEK to Improve Speech Performance
Israeli speech startup VocalZooom, a provider of optical sensors that enable more natural, personalized, and secure voice-control experiences, is partnering with Chinese speech technology firm iFLYTEK, developer of iFlyTek YuDian, the Chinese version of Siri. The partnership will combine VocalZoom's sensor technology with iFLYTEK's Voice Cloud, an intelligent speech platform for mobile cloud and embedded applications
Early tests show VocalZoom's optical sensors dramatically improve the automatic speech recognition performance of iFLYTEK's Voice Cloud by more than 50 percent. The greatest performance enhancement was found in user environments with the highest ambient noise levels, such as driving a car with the windows down.
The VocalZoom multifunction HMC sensor does this by gathering additional data generated during speech, such as facial skin vibrations around the mouth, lips, cheeks, and throat. These facial vibrations can be acquired, measured, and converted to an isolated reference signal with which the system can operate, regardless of noise levels.
VocalZoom's VoiceMatch-in-Sensor technology converts speakers' facial skin vibrations into unique, noise-free voiceprints.
iFLYTEK prepares to launch a headset featuring VocalZoom's optical sensor technology.
Companies will create voice-control solutions combining VocalZoom's Human to Machine Communication (HMC) sensor with Cobalt's speech recognition engine.