Rhino Speech-to-Intent
Java Quick Start

Platforms

• Linux (x86_64)
• macOS (x86_64, arm64)
• Windows (x86_64)
• BeagleBone
• NVIDIA Jetson Nano
• Raspberry Pi (2, 3, 4)

Requirements

• Picovoice Account and AccessKey
• Java 11+

Picovoice Account & AccessKey

Signup or Login to Picovoice Console to get your AccessKey. Make sure to keep your AccessKey secret.

Quick Start

Setup

1. Install JDK 11+ .

2. Install the Java binding from the Maven Central Repository at:

ai.picovoice:rhino-java:${version}

Usage

Create an instance of Rhino that infers intent from spoken commands within a given context :

import ai.picovoice.rhino.*;

Rhino rhino = new Rhino.Builder()
                .setAccessKey("${ACCESS_KEY}")
                .setContextPath("${CONTEXT_FILE_PATH}")
                .build();

Pass in frames of audio to the .process function:

short[] getNextAudioFrame() {
    // ...
    return audioFrame;
}

while(true) {
    boolean isFinalized = rhino.process(getNextAudioFrame());
    if(isFinalized){
        RhinoInference inference = rhino.getInference();
        if(inference.getIsUnderstood()){
            String intent = inference.getIntent();
            Map<string, string> slots = inference.getSlots();
            // .. Use intent and slot values
        }
    }
}

Release resources explicitly when done with Rhino:

rhino.delete();

Custom Contexts

Create custom contexts on Picovoice Console using the Rhino Grammar. Download the custom context file (.rhn) and create an instance of Rhino using the .setContextPath build method.

Non-English Languages

Use the corresponding model file (.pv) to detect non-English contexts. The model files for all supported languages are available on the Rhino GitHub repository .

Pass in the model file using the setModelPath build method to change the detection language:

Rhino rhino = new Rhino.Builder()
                .setAccessKey("${ACCESS_KEY}")
                .setContextPath("${CONTEXT_FILE_PATH}")
                .setModelPath("${MODEL_FILE_PATH}")
                .build();

Demo

For the Rhino Java SDK, we offer demo applications that demonstrate how to use the Speech-to-Intent engine on real-time audio streams (i.e. microphone input) and audio files.

Setup

1. Clone the Rhino repository from GitHub:

git clone --recurse-submodules https://github.com/Picovoice/rhino.git

2. Build the Rhino Java demo using Gradle:

cd rhino/demo/java
./gradlew build

Usage

To see the usage options for the demos, use the -h flag:

java -jar build/libs/rhino-mic-demo.jar -h

Ensure you have a working microphone connected to your system and run the following command to make inferences based on the given context file:

java -jar build/libs/rhino-mic-demo.jar -a ${ACCESS_KEY} -c ${CONTEXT_FILE_PATH}

For more information on our Rhino demos for Java, head over to our GitHub repository .

Resources