Design of AVR Microphone Speech Recognition Circuit Module

Single chip microcomputer STM32L151CCU6

Based on the AVR MCU speech recognition system design, the system uses AVR MCU as the control core to realize the recognition and control of human speech. The main control chip used in the system is Atreel's ATMEGAl28, and the voice recognition function uses ICR oute's single-chip LD3320. The LD3320 integrates a speech recognition algorithm, which eliminates the need for external FLASH and RAM resources and can perform non-specific voice recognition tasks. At the same time, the chip integrates MP3 playback function, supports MPEG and other formats, and can realize voice prompt or MP3 song playback. Thanks to the internal 16-bit A/D, D/A converter and power amplifier circuit, clear sound can be produced without an external power amplifier circuit. The system has reserved various interfaces and has good scalability.

Controller circuit

The controller selects ATMEGA128 chip produced by Atmel Company, adopts advanced RISC structure, and has rich resources such as 128 KB FLASH, 4 KB SRAM and 4 KB E2PROM. The chip is a high performance, low power 8-bit microprocessor in the industry and is widely used in the 8-bit microcontroller market.

LD3320 speech recognition circuit

The LD3320 chip is a "speech recognition" chip. The chip integrates a speech recognition processor and some external circuits, including A/D, D/A converter, microphone interface, sound output interface, etc., and can play MP3. No need to externally connect any auxiliary chip such as FLASH, RAM, etc., directly integrated into the product can realize voice recognition, voice control, man-machine dialogue. Figure 3 shows the schematic diagram of the LD3320 circuit. The SPI bus is used to communicate with the MCU. The clock cannot exceed 1.5MHz.

The microphone working circuit is shown in the figure. The audio output only needs to connect the speaker to SPOP and SPON. When using the SPI bus mode, the MD of the LD3320 should be set high and SPIS set to low. The pins of the SPI bus are SDI, SDO, SDCK and SCS. INTB is the interrupt port. When there is a recognition result or MP3 data is insufficient, an interrupt is triggered to notify the MCU to process. The RSTB pin is the LD3320 reset terminal and is active low. LED1 and LED2 function as power-on indicators.

The feasibility of the design of speech recognition system based on AVR MCU is discussed and the design scheme is given. Through many test results, the system has the advantages of stable circuit operation, high speech recognition rate and low cost. At the same time, with the help of MP3 playback function of LD3320, the system has certain interactivity and entertainment. In terms of portability, the system can easily port the LD3320 driver to various embedded systems with simple modifications. With the demand for artificial intelligence functions, speech recognition technology will be more and more concerned by people. It is believed that speech recognition will have a wider application in the near future.