Voice Biometrics - Android

Introduction

Voice biometrics is a technology that uses the unique characteristics of a person’s voice to identify or authenticate them.

Use cases

Authentication: Verifies if the speaker matches a specific enrolled identity.
Identification: Determines which enrolled user is speaking.

Providers

Feature	TSSV	IDVoice
Accuracy & Performance	Faster, but less accurate	Slower, but more accurate
Result Behavior	Returns results only if confidence ≥ threshold	Returns all results, regardless of confidence
Language Dependency	Language-agnostic	Language-agnostic
Enrollment Flow	Identical for both providers	Identical for both providers
Supported Modes	Text-dependent and text-independent	Text-dependent and text-independent

Audio Format

The input audio data for enrollment and recognition is a 16-bit signed PCM buffer in Little-Endian format. It is always mono (1 channel), and the sample rate 16KHz.

Getting Started

Before you begin, make sure you’ve completed all the necessary preparation steps.
There are two ways to prepare your Android project for Voice Biometrics:

Using sample code
Starting from scratch

From Sample Code

Start by downloading the sample package from the Vivoka Console:

Open the Vivoka Console and navigate to your Project Settings.
Go to the Downloads section.
In the search bar enter package name from table.

📦 sample-voice-biometrics-x.x.x-tssv-android-deps-vsdk-x.x.x.zip or

📦 sample-voice-biometrics-x.x.x-idvoice-tssv-android-deps-vsdk-x.x.x.zip or

📦 sample-voice-biometrics-x.x.x-idvoice-android-deps-vsdk-x.x.x.zip

Once downloaded, you’ll have a fully functional project that you can test, customize, and extend to fit your specific use case.

From Scratch

Before proceeding, make sure you’ve completed the following steps:

1. Prepare your VDK Studio project

Create a new project in VDK Studio
Add the Voice Recognition technology
Export the project to generate the required assets and configuration

2. Set up your Android project

Install the necessary libraries (vsdk-tssv-x.x.x-android-deps-vsdk-x.x.x.zip or vsdk-idvoice-x.x.x-android-deps-vsdk-x.x.x.zip)
Initialize VSDK in your application code

These steps are better explained in the Android Get Started guide.

Start Recognition

1. Initialize Engine

Start by initializing the VSDK, followed by the Voice Recognition engine:

SDK: vsdk-tssv

JAVA

import com.vivoka.vsdk.Vsdk;

Vsdk.init(context, "config/vsdk.json", vsdkSuccess -> {
    if (vsdkSuccess) {
        com.vivoka.vsdk.biometrics.tssv.Engine.getInstance().init(engineSuccess -> {
            if (engineSuccess) {
                // At this point the engine has been initialized.
            }
        });
    }
});

SDK: vsdk-idvoice

JAVA

import com.vivoka.vsdk.Vsdk;

Vsdk.init(context, "config/vsdk.json", vsdkSuccess -> {
    if (vsdkSuccess) {
        com.vivoka.vsdk.biometrics.idvoice.Engine.getInstance().init(engineSuccess -> {
            if (engineSuccess) {
                // At this point the engine has been initialized.
            }
        });
    }
});

Different SDKs will give you different results, for example vsdk-idvoice reports varying results as it analyzes the audio, while vsdk-tssv only sends you result if the engine thinks it is acceptable (depending of the conﬁdence level you set).

We recommend that you try it out the application in real situation to select your custom minimum score required to satisfy your need in false rejection and false acceptation. But by default you can just check if the score is above 0.

You cannot create two instances of the same engine.

If you call Engine.getInstance() multiple times, you will receive the same singleton instance.

2. Enroll users

JAVA

Model model = Engine.getInstance().getModel("model-1", ModelType.TEXT_INDEPENDANT);
Model model = Engine.getInstance().getModel("model-1", ModelType.TEXT_DEPENDANT);

Models contain enrollment data that recognition operations need.

If a model was previously created with the same name it will be loaded. You can check enrolled users with:

JAVA

if (model.getUsers().size() == 0) {
  // No enrolled users.
}

Adding a user to the model

JAVA

// model.addRecord(String name, Buffer buffer);
model.addRecord("victorien", buffer);

The more data you give the model, the better the result will be.
Prefer to register the data in the condition of the use case of the model.

The format is preferred to be 16Khz mono-channel.

3. Identify

JAVA

import com.vivoka.vsdk.biometrics.Identificator;

Identificator identificator = Engine.getInstance().getIdentificator("ident", model,
    (resultType, resultStatus, result, isFinal) -> {
        Log.e("IdentificatorResult", result.toString());
        final String name = result.optString("name");
        final double probability = result.optDouble("probability");
        final double score = result.optDouble("score");
    }
});

4. Authenticate

JAVA

import com.vivoka.vsdk.biometrics.Authenticator;

Authenticator authenticator = Engine.getInstance().getAuthenticator("ident", model,
    (resultType, resultStatus, result, isFinal) -> {
        Log.e("AuthenticatorResult", result.toString());
        final String name = result.optString("name");
        final double probability = result.optDouble("probability");
        final double score = result.optDouble("score");
    }
});
authenticator.setUserToRecognize("victorien");

5. Release Engine

JAVA

Engine.getInstance().release();