レイトロン List of Products and Services

Latetron Co., Ltd. conducts research and development of algorithms in the fields of "audio, video, and wireless communication" through industry-academia collaboration, creating unique core technologies. By conducting deeper research and development of core technologies in "audio, video, and wireless communication," we aim to solve the anxieties and frustrations of the elderly and people with disabilities, proposing an environment that enables them to lead independent daily and social lives, thereby contributing to a barrier-free and universal design society. 【Business Activities】 ■ Semiconductor system LSI design and development ■ Development, manufacturing, and sales of system devices ■ Sales of semiconductors, electronic components, and electronic devices ■ Research and development of core technologies and commercialization *For more details, please refer to the PDF materials or feel free to contact us.

• others

"LisPee360" is a voice recognition smart controller that can pick up human speech from a distance even in noisy environments, allowing you to control home appliances with voice commands via an infrared remote control. Since it does not connect to the internet, there is no need for complicated initial setup such as obtaining addresses or accounts for smartphones or Wi-Fi routers, making it easy to use even for those who are not tech-savvy. It does not send personal data such as voice recordings to external sources like the cloud, so you can use it with peace of mind. 【Features】 ■ Home appliance control function ■ Home appliance control combo function ■ Schedule management function ■ Timer function *For more details, please refer to the PDF document or feel free to contact us.

• others

We are pleased to introduce our new brand, "LisPee Technology." Equipped with the voice recognition engine "VoiceMagic," it can distinguish voices from a distance in noisy environments, eliminating the need to call out names during voice recognition with its Always Listening feature. Furthermore, by processing with a dedicated LSI, it can differentiate human voices in about 0.2 seconds, respond in real-time, and control devices immediately, achieving a natural response without any discomfort. We offer a robot-type voice recognition smart controller "Chapit mini" and a 360° omnidirectional operation dome-type "LisPee 360." 【Features】 ■ Distinguishes voices from a distance in noisy environments ■ Equipped with Always Listening feature ■ Differentiates human voices in about 0.2 seconds ■ Responds in real-time *For more details, please refer to the PDF document or feel free to contact us.

• others

"Chapit" is a next-generation communication robot that assists with daily life through conversation, allowing users to experience a near-future lifestyle with its adorable appearance and convenient features. It has a strong noise resistance and a high recognition rate for phrase voice recognition, making it capable of understanding commands even amidst the noise of everyday life. Additionally, it is equipped with a learning remote control function, allowing it to memorize the remote control signals of home appliances. This enables the product to function as a voice remote control, operating various appliances. [Features] ■ Communication function ■ Home appliance control function ■ Recreation function ■ Time support function *For more details, please refer to the PDF document or feel free to contact us.

• others

"VoiceMagic" is a noise-resistant voice recognition engine with a high recognition rate. It can recognize voice from a distance of 2 to 3 meters from the microphone in noisy real-life environments. The Always Listening feature allows for completely hands-free operation without the need to press a switch when recognizing speech. Additionally, it does not require a communication line or network connection, enabling real-time responses at all times. 【Features】 ■ High recognition rate (over 98% recognition rate at SNR 20dB) from a distance from the microphone ■ Prevents misrecognition of input voice that is not part of registered phrases, improving recognition accuracy ■ No need for speaker voice registration (supports unspecified speakers) ■ Allows for handling of similar words by classifying registered phrases by scene (up to 16 scenes) ■ Does not require high-performance CPUs or DSPs in the devices it is installed on ■ Supports a variety of input voice formats *For more details, please refer to the PDF document or feel free to contact us.

• Other Management Services

The "RPSCO1-O1E" is a scream recognition module that identifies and notifies the characteristics of women's screams using proprietary technology. Developed using unique voice recognition technology. It automatically recognizes screams to protect individuals from danger, immediately reports upon recognition of a scream, and helps prevent incidents and accidents before they occur. 【Features】 ■ Capable of recognizing relatively low-volume screams (sensitivity adjustable) ■ Scream judgment status can be monitored via indicator output ■ Compatible with condenser microphones (dynamic microphones can also be connected with adjustments) ■ Recognition sensitivity can be set in 16 levels ■ Recognition frequency range is 600Hz to 5.5KHz *For more details, please refer to the PDF document or feel free to contact us.

• Elevator

When you select one phrase from the pre-registered phrases and input it via voice, the recognition engine (voice recognition LSI) compares it with the group of phrases in the database (training data) and calculates the index assigned to the closest phrase along with its likelihood value. You can choose one of three types of host serial interfaces for the connection with the host.

• others