Porcupine Wake Word Engine + Rhino Speech-To-Intent Engine Demo for Arduino (English language)

This package contains a demo project with examples for Arduino using Porcupine Wake Word Engine in conjunction with Rhino Speech-to-Intent Engine.

Compatibility

• Arduino Nano 33 BLE Sense

AccessKey

The Porcupine and Rhino SDKs require a valid AccessKey at initialization. AccessKeys act as your credentials when using Porcupine and Rhino SDKs. You can get your AccessKey for free. Make sure to keep your AccessKey secret. Signup or Login to Picovoice Console to get your AccessKey.

Installation

1. Install the Arduino IDE for your platform.
2. With the IDE open, go to Tools->Manage Libraries...
3. Search for Picovoice_EN, then click INSTALL.

This demo package is intended to be used via the Arduino Library Manager.

Demo

The package contains only the Intent-Based Voice Assistant demo. To access the demo:

1. Open File->Examples->Picovoice_EN->IntentBasedVoiceAssistantExample.
2. Replace ACCESS_KEY in the source with the AccessKey obtained from Picovoice Console.
3. Press Upload and check the Serial Monitor for outputs.

Additional information can be found in the Picovoice docs for Porcupine and Rhino.

Create Custom Wake Word

1. Compile and upload the Porcupine_EN/GetUUID sketch from the File -> Examples menu. Copy the UUID of the board printed at the beginning of the session to the serial monitor.
2. Go to Picovoice Console to create models for Porcupine wake word engine.
3. Select Arm Cortex M as the platform when training the model.
4. Select your board type (Arduino Nano 33 BLE Sense) and provide the UUID of the chipset on the board.

The model is now being trained. You will be able to download it within a few hours.

Import the Custom Wake Word

1. Download your custom voice model(s) from Picovoice Console.
2. Decompress the zip file. The model for Porcupine wake word is located in two files: A binary .ppn file, and as a .h header file containing a C array version of the binary model.
3. Copy the contents of the array inside the .h header file and update update the DEFAULT_KEYWORD_ARRAY values in pv_params.h.

Create Custom Context

1. Compile and upload the Rhino_EN/GetUUID sketch from the File -> Examples menu. Copy the UUID of the board printed at the beginning of the session to the serial monitor.
2. Go to Picovoice Console to create a context for Rhino speech to intent engine.
3. Select Arm Cortex M as the platform when training the model.
4. Select your board type (Arduino Nano 33 BLE Sense) and provide the UUID of the chipset on the board.

Import the Custom Context

1. Download your custom voice model(s) from Picovoice Console.
2. Decompress the zip file. The model for Rhino speech to intent is located in two files: A binary .rhn file, and as a .h header file containing a C array version of the binary model.
3. Copy the contents of the array inside the .h header file and update the CONTEXT_ARRAY values in pv_params.h.