Genesys Cloud - Main

 View Only

Sign Up

  • 1.  Transcription accuracy issue with Copilot (Dictionary term not resolving)

    Posted 2 days ago

    Hi everyone,

    We are currently using Agent Copilot and have identified an issue with transcription accuracy.

    For example, the word "Okta" is being transcribed as "Octa" in the interaction transcript, and this then carries through to the Copilot-generated summary.

    We have already added "Okta" in Dictionary Management, however it is still not being picked up correctly in the transcript or summary.

    Has anyone experienced a similar issue?
    Is there a way to improve transcription accuracy for specific terms?

    Appreciate any guidance.

    Thanks!


    #AICopilot(Agent,SupervisorAdmin)

    ------------------------------
    Phaneendra
    Technical Solutions Consultant
    Monash University
    Australia
    ------------------------------


  • 2.  RE: Transcription accuracy issue with Copilot (Dictionary term not resolving)
    Best Answer

    Posted yesterday

    Hey Phaneendra,

    I saw in the Dictionary Management article, they refer to this "Dictionary management is only supported for Genesys Cloud native transcription dialects." Understand dictionary management View summary - Genesys Cloud Resource Center  

    I'm wondering that it might not be resolving because of the transcription setting for Copilot?

    I guess the easiest way to test this would be have a user without Copilot say Okta a bunch in an interaction and then check the transcription and see if it uses Okta instead of Octa.



    ------------------------------
    Robert Niblock
    Contact Centre Technology Analyst
    ------------------------------

    Original Message


  • 3.  RE: Transcription accuracy issue with Copilot (Dictionary term not resolving)

    Posted 21 hours ago

    Thanks for the suggestion Robert, that's a good point.

    We're using the en-AU dialect with Genesys native transcription, so dictionary management should be supported. I'll run a test interaction without Copilot to confirm whether "Okta" is still being transcribed as "Octa" at the base transcript level.

    If the transcript itself is still showing "Octa" despite the dictionary entry, would that indicate a dialect/configuration limitation, or is there an additional step required to improve recognition accuracy for specific terms?

    I'll report back once I've tested.

    Appreciate the help.



    ------------------------------
    Phaneendra
    Technical Solutions Consultant
    Monash University
    Australia
    ------------------------------

    Original Message


Related Content