Porcupine - Android API

  • Wake Word Engine
  • Offline Voice Commands
  • Local Speech Recognition
  • Always Listening
  • Android
  • Java

This document outlines how to integrate Porcupine wake word engine within an Android application.

Prerequisites

Porcupine is implemented in ANSI C and is shipped as precompiled libraries accompanied by corresponding Java interfaces (bindings). To integrate within an Android application the following items are needed

  • Precompiled libraries
  • Java binding
  • The model file. The standard model is freely available on Porcupine's GitHub repository. Enterprises who are commercially engaged with Picovoice can access compressed and standard models as well.
  • Keyword file(s) for your use case. A set of freely-available keyword files can be found on Porcupine's GitHub repository. Enterprises who are engaged with Picovoice can create custom wake word models using Picovoice Console.

Integration

Porcupine provides a binding for Android using JNI. It can be initialized using.

final String modelFilePath = ...
final String keywordFilePath = ...
final float sensitivity = 0.5f;
Porcupine porcupine = new Porcupine(
modelFilePath,
keywordFilePath,
sensitivity);

Sensitivity is the parameter that enables developers to trade miss rate for false alarm. It is a floating number within [0, 1]. A higher sensitivity reduces miss rate at cost of increased false alarm rate.

Once initialized, porcupine can be used to monitor incoming audio.

private short[] getNextAudioFrame();
while (true) {
final boolean result = porcupine.process(getNextAudioFrame());
if (result) {
// detection event logic/callback
}
}

Finally, be sure to explicitly release resources acquired by porcupine as the binding class does not rely on the garbage collector for releasing native resources.

porcupine.delete();