Introduction  

The VIDIZMO Audio Indexer App provides detection and redaction capabilities utilizing AI models. One key capability is detecting and redacting Personal Identifiable Information (PII) from transcribed audio and video files. To utilize this, you must configure the VIDIZMO Audio Indexer App in the VIDIZMO portal.  


If you want to learn more about this functionality, visit Understanding PII Detection and Redaction using VIDIZMO Audio Indexer 


Note: To perform the PII detection, you need your audio or video files that need to have transcriptions. The VIDIZMO Audio Indexer app will automatically generate transcriptions if you have configured it for PII detection. You can also add transcriptions using the following ways: 


Pre-requisites 

  • Ensure that you log into your VIDIZMO Portal as an Administrator or Manager.  
  • If you want to redact the detected PII, you must also have Redaction as part of your VIDIZMO package. This will also display the ‘Redaction Type’ field and the ‘Advanced Processing’ options in the VIDIZMO Audio Indexer. 

 Navigating to VIDIZMO Audio Indexer  

  1. Use the button at the top left to open the action menu. 
  2. Click the 'Admin' dropdown. 
  3. Select ‘Portal Settings.’ 



4. While in ‘Portal Settings’, click ‘Apps.’ 

5. Select ‘Content Processing.’   

6. Use the settings icon to enter the VIDIZMO Indexer App's settings. 



Configuring the Audio Indexer for PII

  1. Media Formats: Select the Evidence or Media Formats you want to perform the PII Detection on. Select Audio for sound-only files and select Video if your file includes both sound and visuals. If you are on an EVCM Portal, this field appears as ‘Media Formats.’
  2. Insights: Select the PII entities that you want to detect in your content, see PII Entities for a list of PIIs entities available. To add custom PIIs, contact support to include additional PII for detection in the insights field. You can also add other AI Insights (such as Chaptering) in this field to generate them for your content alongside PII detection or redaction. 
  3. Redaction Types: Choose the PII entities you wish to redact from your audio or video by selecting them from the drop-down menu. If any PII entity is added in this field, then it reveals the ‘Advanced Processing’ options.  
  4. Confidence Score: Set the confidence score for the model to recognize a detected term as a PII entity. For the system to identify a detected term as PII, its value must exceed this default minimum value. The confidence score can be set from 0 to 100, with 35 being the recommended value. 
  5. Excluded Words: Provide a list of words that will not be detected as PII or not be marked as PII even if they are already defined as a PII within the application. For example, 'John' is considered a PII entity, but adding 'John' to ‘Excluded Words' will prevent the application from identifying it as PII. Note that this field is case sensitive. 
  6. Context Keywords: Provide the context words that the model will analyze to improve the confidence score of the custom PII entity.   
  7. Time Interval Threshold: Specify the time interval threshold (in milliseconds) for more accurate redaction of PII. The threshold value determines which PIIs will be selected during audio activity detection, and then apply the configured ‘Start Time’ and ‘End Time’ corrections on the audio segments for complete and precise redaction. 
  8. Start Time Correction: Specify a value (in milliseconds) for how much the start time of a PII detection activity will be adjusted by. Helpful in cases when the beginning part of a PII is skipped during detection. For instance, if "John" is left out from the PII "John Doe," the start time correction can help in capturing the entire PII for complete classification. 
  9. End Time Correction: Specify a value (in milliseconds) for how much the end time of a PII detection activity will be adjusted by. Helpful in cases when the ending part of a PII is skipped during detection. For instance, if "Doe" is left out from the PII "John Doe," the end time correction can help in capturing the entire PII for complete classification. 
  10. Original File Handling: Select how you want to handle the content that undergoes PII detection or redaction activity after the processing is finished. This setting only applies when Automatic Processing is turned on. 
    1. Retain File: The original content remains unaffected, while a copy is created, processed for PII Insights and then published.  
    2. Delete and Move to Recycle Bin: The original content is deleted and moved to the Recycle Bin, while a copy of the content is processed for PII Insights and then published. 
    3. Override Original File: The original content is processed for PII Insights while it remains published. No copies are made, and the content is not relocated anywhere. 

11. Automatic Processing: Determine if you want to enable automatic processing which automatically redacts PII from your content as soon as it is added to your Portal. 

12. Click ‘Save Changes’ to save and finalize your application settings. 



13. Make sure you have the application enabled so that you can process your content according to your configurations. 



For a guide on performing PII detection and redaction on your content, visit How to Detect and Redact PII using VIDIZMO Audio Indexer