Eagle Speaker Recognition
iOS Quick Start

Platforms

• iOS (13.0+)

Requirements

• Xcode
• CocoaPods

Picovoice Account & AccessKey

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

Overview

Eagle Speaker Recognition has two distinct steps: Enrollment and Recognition. In the enrollment step, Eagle analyzes a series of utterances from a particular speaker to learn their unique voiceprint. This step produces an Eagle Profile object, which can be stored and utilized during inference. During the Recognition step, Eagle compares the incoming frames of audio to the voiceprints of all enrolled speakers in real-time to determine the similarity between them.

Quick Start

Setup

1. Install Xcode.

2. Install CocoaPods

3. Import the Eagle-iOS pod by adding the following line to the project's Podfile:

pod 'Eagle-iOS'

4. Run the following from the project directory:

pod install

Usage

Speaker Enrollment

1. Create an instance of the profiler:

import Eagle

let accessKey: String = "${ACCESS_KEY}"
do {
    let eagleProfiler = try EagleProfiler(accessKey: accessKey)
} catch { }

2. Pass the enrollment audio data to the profiler until the enrollment percentage reaches 100%:

func get_next_enroll_audio_data() -> [Int16] {
    // ...
}

do {
    var percentage = 0.0
    var feedback: EagleProfilerEnrollFeedback?
    while (percentage < 100.0) {
        (percentage, feedback) = try eagleProfiler.enroll(pcm: get_next_enroll_audio_data())
    }
} catch { }

3. Export the speaker profile:

let speakerProfile = try eagleProfiler.export()

4. Release the resources acquired by the profiler:

eagleProfiler.delete()

Speaker Recognition

1. Create an instance of Eagle Speaker Recognition:

let eagle = Eagle(accessKey: accessKey, speakerProfile: speakerProfile)

2. Pass the incoming audio stream to Eagle Speaker Recognition:

func get_next_audio_frame() -> [Int16] {
    // ...
}

do {
    let profileScores = try eagle.process(pcm: get_next_audio_frame())
} catch { }

3. Release the resources acquired by Eagle Speaker Recognition:

eagle.delete()

Demo

For the Eagle Speaker Recognition iOS SDK, we offer a demo application that demonstrates how to use the speaker recognition engine on microphone audio.

Setup

Clone the Eagle Speaker Recognition repository from GitHub using HTTPS:

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

Usage

1. Before building the demo app, run the following to install the Eagle Speaker Recognition CocoaPod:

cd eagle/demo/ios/
pod install

2. Replace "${YOUR_ACCESS_KEY_HERE}" inside the ViewModel.swift file with your AccessKey obtained from Picovoice Console.

3. Open EagleDemo.xcworkspace and run the demo.

For more information on our Eagle Speaker Recognition demo for iOS, head over to our Github repository.

Resources