Package ai.picovoice.rhino

Class Rhino

java.lang.Object

ai.picovoice.rhino.Rhino

public class Rhino
extends java.lang.Object

Java binding for Rhino Speech-to-Intent engine. It directly infers the user's intent from spoken commands in real-time. Rhino processes incoming audio in consecutive frames and indicates if the inference is finalized. When finalized, the inferred intent can be retrieved as structured data in the form of an intent string and pairs of slots and values. The number of samples per frame can be attained by calling getFrameLength() . The incoming audio needs to have a sample rate equal to getSampleRate() and be 16-bit linearly-encoded. Rhino operates on single-channel audio.

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	Rhino.Builder	Builder for creating an instance of Rhino with a mixture of default arguments

Field Summary

Fields

Modifier and Type	Field	Description
static java.lang.String	LIBRARY_PATH
static java.lang.String	MODEL_PATH

Constructor Summary

Constructors

Constructor	Description
Rhino(java.lang.String accessKey, java.lang.String libraryPath, java.lang.String modelPath, java.lang.String contextPath, float sensitivity, float endpointDurationSec, boolean requireEndpoint)	Constructor.

Method Summary

Modifier and Type	Method	Description
void	delete()	Releases resources acquired by Rhino.
java.lang.String	getContextInformation()	Getter for context information.
int	getFrameLength()	Getter for number of audio samples per frame.
RhinoInference	getInference()	Gets inference result from Rhino.
int	getSampleRate()	Getter for audio sample rate accepted by Picovoice.
java.lang.String	getVersion()	Getter for version.
boolean	process(short[] pcm)	Processes a frame of audio and emits a flag indicating if the inference is finalized.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

LIBRARY_PATH

public static final java.lang.String LIBRARY_PATH

MODEL_PATH

public static final java.lang.String MODEL_PATH

Constructor Detail

Rhino

public Rhino(java.lang.String accessKey,
             java.lang.String libraryPath,
             java.lang.String modelPath,
             java.lang.String contextPath,
             float sensitivity,
             float endpointDurationSec,
             boolean requireEndpoint)
      throws RhinoException

Constructor.

Parameters:

accessKey - AccessKey obtained from Picovoice Console (https://console.picovoice.ai/)

libraryPath - Absolute path to the native Rhino library.

modelPath - Absolute path to the file containing model parameters.

contextPath - Absolute path to file containing context parameters. A context represents the set of expressions (spoken commands), intents, and intent arguments (slots) within a domain of interest.

sensitivity - Inference sensitivity. It should be a number within [0, 1]. A higher sensitivity value results in fewer misses at the cost of (potentially) increasing the erroneous inference rate.

endpointDurationSec - Endpoint duration in seconds. An endpoint is a chunk of silence at the end of an utterance that marks the end of spoken command. It should be a positive number within [0.5, 5]. A lower endpoint duration reduces delay and improves responsiveness. A higher endpoint duration assures Rhino doesn't return inference preemptively in case the user pauses before finishing the request.

requireEndpoint - If set to `true`, Rhino requires an endpoint (a chunk of silence) after the spoken command. If set to `false`, Rhino tries to detect silence, but if it cannot, it still will provide inference regardless. Set to `false` only if operating in an environment with overlapping speech (e.g. people talking in the background).

Throws:

RhinoException - If there is an error while initializing Rhino.

Method Detail

delete

public void delete()

Releases resources acquired by Rhino.

process

public boolean process(short[] pcm)
                throws RhinoException

Processes a frame of audio and emits a flag indicating if the inference is finalized. When finalized, getInference() should be called to retrieve the intent and slots, if the spoken command is considered valid.

Parameters:

pcm - A frame of audio samples. The number of samples per frame can be attained by calling getFrameLength(). The incoming audio needs to have a sample rate equal to getSampleRate() and be 16-bit linearly-encoded. Furthermore, Rhino operates on single channel audio.

Returns:

Flag indicating whether the engine has finalized intent extraction.

Throws:

RhinoException - if there is an error while processing the audio frame.

getInference

public RhinoInference getInference()
                            throws RhinoException

Gets inference result from Rhino. If the spoken command was understood, it includes the specific intent name that was inferred, and (if applicable) slot keys and specific slot values. Should only be called after the process function returns true, otherwise Rhino has not yet reached an inference conclusion.

Returns:

The result of inference as a RhinoInference object.

Throws:

RhinoException - if inference retrieval fails.

getContextInformation

public java.lang.String getContextInformation()
                                       throws RhinoException

Getter for context information.

Returns:

Context information.

Throws:

RhinoException

getFrameLength

public int getFrameLength()

Getter for number of audio samples per frame.

Returns:

Number of audio samples per frame.

getSampleRate

public int getSampleRate()

Getter for audio sample rate accepted by Picovoice.

Returns:

Audio sample rate accepted by Picovoice.

getVersion

public java.lang.String getVersion()

Getter for version.

Returns:

Version.