Postech Academy-Industry Foundation

Kyeong Won Jeong

Hong June Park

Dong Hee Yeo

Hyeon Kyu Noh

Seong Eun Cho

Won Cheol Lee

Young Jae Jang

The present invention relates to a real-time voice recognition apparatus equipped with an application-specific integrated circuits (ASIC) chip and a smartphone, capable, by using one smartphone and one ASIC chip and without using a cloud computer, of assuring personal privacy, and, due to a short delay time, enabling real-time conversion of voice input signals into text for output. When one DRAM chip is optionally added to the real-time voice recognition apparatus, the number of neural network layers is increased thereby significantly improving accuracy of conversion of voice input signals into text.

Real-time voice recognition apparatus equipped with ASIC chip and smartphone

The present invention relates to a microphone with a specific audible area using ultrasound wave, which emits an ultrasound wave toward a sound source positioned in a specific area within a desired distance and a desired direction from the microphone, and extracts a sound signal in an audible frequency range, generated by the sound source, from an ultrasound wave reflected and received from the sound source. The microphone with a specific audible area using ultrasound wave can limit the audible area to an area within a specific angle from a half line starting from the microphone and a specific distance from the microphone, such that a user can selectively hear a desired sound in a noisy environment. When the microphone is applied to a hearing aid, the user can hear only the audible sound generated by the sound source located within the specific audible area in front of the user with the surrounding noise removed.

Microphone with specific audible area using ultrasound wave

Growing community of inventors

Busan, South Korea

Kyeong Won Jeong