Method of realizing speech recognition with MSP432

Jacktang

Method of realizing speech recognition with MSP432 [Copy link]

In a world where everything is connected, more and more electronic devices that can understand speech are coming into our sight. In devices such as smartphones, tablets and laptops with Siri or Cortana applications, speech recognition can help users search for answers or control the electronic devices around them. Although these applications are eye-catching, they take up a lot of processing power and memory. So it’s no surprise that people misunderstand that microcontrollers (MCUs) are too small to recognize speech.

Yes, the low power and small size of an MCU make it insufficient for understanding the full range of speech content, but for small, low-power embedded applications, perhaps only a few well-defined phrases, such as "heat up my coffee" or "turn off the lights," may be enough. Texas Instruments (TI) recently demonstrated this capability on its low-power MSP432 MCU at CES.

TI has also released a speech recognizer library written in C language code , which enables MSP432 MCU-based applications to recognize the user's frequently used voice phrases, ignoring other voice content, and can recognize up to 11 phrases. Although the user must repeat the phrases they want to be recognized several times during the setup, once this step is successfully completed, it can be used smoothly afterwards.

This speech recognizer library has many exciting features, such as:

• Users can change their phrases at any time
• Users can set the recognizer to respond to only a few phrases
• Of course, users can also delete certain phrases in the phrase library according to their personal needs.

In addition, along with the speech recognition library, some easy-to-use header files and user and API guides are provided to help users get started quickly. The download also includes example demonstration programs for MSP432 MCU LaunchPad development kits, Audio BoosterPack plug-in modules, and Sharp or Kentec LCD BoosterPack kits.

This demo application uses the 14-bit analog-to-digital converter (ADC14) integrated in the MSP432 MCU to collect speech, and a liquid crystal display (LCD) to display a menu. This menu successfully runs the recognition function, and the user can choose:

• You start by saying a phrase that you want the recognizer to remember. The recognizer will generate a model for this speech and store it in flash memory (a task called enrollment).
• Say the enrolled phrase again. The recognizer will use it to make a better model to improve performance (a task called updating).
• Delete the first model registered
• Run Identification Function