NRK10 offline voice recognition chip

☆ Disposable OTP burning, plug -in SPI_FLASH PWM/DAC? Output, you can directly drive 8 Euros 0.5W speakers;
☆ Fixed entry, non -specific identification, can identify 20 entries;
☆ The identification effect: quiet and no echo environment, the recognition rate within 2 meters can reach 90%or more, and the distance can reach 5 meters;
☆ The built -in MIC level 2 partial pressure amplifier circuit, as well as the self -supporting AGC gain control, and the rate noise circuit;
☆ Package form: LQFP32/COB;

INQUIRY DOWNLOAD

PRODUCT INFORMATION

NRK10 voice recognition chip is a high-performance, low-cost offline voice recognition chip independently developed by Guangzhou Jiuxin Electronics. It has voice recognition and broadcast functions. It requires plug-in SPI-FLASH, storage entry or voice broadcast content. He has the advantages of high recognition rate, industrial -level performance, easy -to -use, and easy to update the entry. It is widely used in various fields such as smart homes, AI artificial intelligence, toys.

2. Product characteristics:

working voltage: 3.3V ~ 5.5V, generally 4.2V

dormant current: <7UA

Unbeatable to wait for the current: 25 ~ 50mA

Wake -up method: After dormancy, you can wake up from any GPIO, RTC, or WDT interruption to enter the standby state; in the standby state, enter the working state by waking words or entries.

fixed entry, non -specific person recognition

Can identify 20 entries (each word is recommended for three or more), with a total number of words between 50 and 60 words.

Identification environment: quiet and no echo.

Identification effect: quiet and no echo environment, the recognition rate within 2 meters can reach 90%or more, and the distance can reach 5 meters.

Identification language: 32 types of languages, such as English, Chinese, Japanese, Cantonese, etc. (Do not recognize a variety of languages at the same time, that is, one module cannot recognize Chinese, English, Japanese).

PWM output can directly drive 8 Euros 0.5W speakers; DAC output, which can be connected to the power amplifier.

The content of the audio output needs to be placed in the plug -in spi_flash. Then, then

Low voltage reset: less than 1.6V chip for reset

3.3V, defaults to 3.3V.

working temperature: -10 & deg; c ~+70 & deg; C.

The chip program and entry storage method are OTP storage methods, & bull; disposable records, all of which are in the main control chip, which is convenient for samples and mass production. The voice of the broadcast is stored in the plug -in SPI Flash. Support 8M/16M/32Mbit SPI Flash.

built -in UART serial port, convenient for single -chip microcomputer control and communication.

built -in MIC 2 partial pressure amplifier circuit, as well as self -supported AGC gain control, and a rate noise circuit.

The form of packaging includes LQFP32, COB.

4. Function introduction

4.1, UART serial function introduction

NRK10 voice recognition chip built -in standard UART asynchronous serial interface, the communication data format is: starting bit: 2 digits; FA; data bit: 2 digits; 00h ~ ffh; verification digit: 2 digits, the verification digit and the data bit are added For FFH. Use the computer serial port to determine the assistant, you need to set the parameters of the serial port correctly, and set the figure:

4.2. Play control introduction

Introduction to the entry: The entry refers to the entry of the standard version of the identification instructions we want to say & ldquo; Xiaoming & rdquo; as a wake -up word, we can identify other entries after waking up. For details, please refer to the table below:

Note: 1. This version can be directly connected to PA10 without serial version chip PA10, PA11 directly connects the lights; you can also use the serial version PA6, PA7 to directly output serial signal 2. Standard version entry for testing. If you want to modify the entry, please contact the business, please contact the business Personnel 3. UART port can be used with a single -chip microcomputer. 4. The delay time is 10 seconds after the wake -up. After receiving the instructions, re -count the time.

5. Circuit diagram

(Principle diagram without serial version of the circuit)

(Principle diagram with serial port version of the circuit)

Guangzhou Nine Chip Electronic Technology Co., Ltd. was founded in Tianhe District, Guangzhou. The company is headquartered in Tianhe District, Guangzhou. Our company is a company's development, voice product solution design, voice product production, and voice -up software development.Smart home, smart home appliances, Internet of Things services, high -tech companies that integrate soft hardware strength.