LcT has developed a software solution that significantly improves voice communication quality and speech recognition performance on mobile devices. Our solution contains the following technologies:
Our software solution can be implemented on existing cell phone or tablet processors. Our solution supports HD voice. There is no need for special DSP hardware.
Dual Microphone Array for Mobile Devices
Li Creative Technologies (LcT) has developed a dual microphone array for smartphones and tablets that dramatically improves voice quality when video or web conferencing and using speakerphone, and improves the accuracy of Siri and other speech recognition applications. Our software solution utilizes advanced digital signal processing algorithms, including sound source localization, adaptive beam forming, and noise reduction, to suppress background noise while enhancing the speech signal. LcT's beam forming and noise reduction algorithms can improve the signal-to-noise ratio (SNR) by up to 30 dB. Compared side by side with an industry leading smartphone with three microphones, the SNR of our solution was 5 dB better and frequency distortion 20 to 30 dB less at various frequency bands.
- Dual microphone array
- Adaptive beam forming
- Noise reduction
- Up to 30 dB SNR Improvement
- Speech recognition (Siri, Dragon)
- Video conferencing (FaceTime, Skype)
- Web conferencing (GoToMeeting, Adobe Connect, WebEx)
- Speakerphone calls
Low Cost Software for Licensing
Our software solution works on any mobile device with two microphone input. LcT can provide acoustic design guidance and tune our software to provide best performance. Since LcT’s engineers are experienced working with a variety of platforms, the implementation will be fast and the new system will have the same performance as our prototype systems. There is no need for an audio DSP chip. Our software solution is not only lower in cost compared to an audio DSP chip solution but also saves on power consumption and space.