Overview

The following use case is a guide for your app development. The below use case describes recording the audio sample and generating the score for Mental Fitness.

Notes:

• Please check Sonde EDGE SDK setup at IOS EDGE SDK

As a developer, I want to measure voice characteristics of user’s mental-fitness health condition

Perform the below steps on the app side to generate the score:

STEP 1: Display the prompt and duration to the user
STEP 2: Record 30 seconds audio file
STEP 3: Generate the inference score for Mental Fitness
STEP 4: Display the score to the user.

STEP 1: Display the prompt and duration to the user

Open

 :

STEP 2: Record 30 seconds audio file

1. Before starting the audio recording, add the following check to make sure that the recording permission is enabled in the app. To access the AVAudioSession import AVFoundation in your respective file. If the audio permission is granted by the user, then audio recording can be initiated.
   
   

   import AVFoundation

    

   func askForAudioPermission(){ let permission = AVAudioSession.sharedInstance().recordPermission switch permission { case AVAudioSession.RecordPermission.denied: print("Permission denied") default: AVAudioSession.sharedInstance().requestRecordPermission({ [weak self] (granted: Bool) -> Void in guard let self = self else { return } DispatchQueue.main.async { if granted { print("permissionGranted") } else{ print("Permission denied") } } }) } }

    

2. Create an instance of AudioRecorder class and call startRecording()function to start recording.
   To access the AudioRecorder class import Sonde_SDK in your project.
   
   

   import Sonde_SDK

STEP 3: Generate the inference score for Mental Fitness

After recording the audio file, scoring for Mental Fitness can be initiated. To generate the score, follow the below steps:

1. Create the MetaData instance; for that, you will be requiring the gender and year of birth of the user. You can pass the gender value as .male or .female, yearOfBirth and partnerId as String type. The partnerId should be a unique UDID that the Partner has assigned to the end user and should not be user's email, cell, or other identifying data).
   
   

    

2. Create the instance of InferenceEngine class that accepts the metadata instance from the above step and call inferScore() function with audioFilePath, healthCheckType, scoreHandler, and errorHandler as parameters.
   audioFilePath: generated audio file from step 2
   healthCheckType: health condition for which you want to generate the score, in this case, it will be MENTAL_FITNESS
   scoreHandler: callback when the score is generated
   errorHandler : callback if there is an error
   
   

    

3. Typecast the score to VFFinalScore to get the other voice features scores.

Voice Sufficiency Check

We have introduce voice sufficiency checks in our SDK, enhancing the audio quality for Mental Fitness Score assessments, ensuring only audio files containing speech and meeting the SNR threshold are getting scored.
Developers needs to integrate error responses ( Low Speech; High Noise; Low Speech and High Noise) mentioned in section errorHandler : callback if there is an error

STEP 4: Display the score to the user

Open