Troubleshooting Dictation Recognition Issues (Administrator Process)
  • 4 Minutes to read
  • Dark
    Light

Troubleshooting Dictation Recognition Issues (Administrator Process)

  • Dark
    Light

If a user is having issues with recognition of dictation transcripts, an administrator should follow the steps below:  


  1. Add uncommon words that are not returning correctly to the user's Account Vocabulary. 
    • This includes names of people, places, products, or even uncommon drug names
    • Be sure to TEST IN DICTATION before adding to vocabulary to make sure the word or phrase isn't already in the dictionary or topic.
    • If it's a term that will be dictated by others, it's fine to add the term to organization vocabulary for the organizations that are likely to dictate it. If it's just something that will be dictated by one person, add it to their Account vocabulary.
    • Common medical terms that are not returning correctly should be reported to nVoq Support.

       
  2. Listen to the audio from the dictations on the Review & Correct page in nVoq.Administrator. 
    • If the dictation audio is poor due to microphone issues (not background noise), there may be a problem with the user's microphone.
      • If the user is dictating on a computer:
        • The user may need to disable extraneous microphones. See Enable Microphone
        • Make sure the recording was made using a recording device that is approved by nVoq for use with the voice client. You can see which microphone was used for the dictation on the Review & Correct Dictation Event Timeline. Using a device that has NOT been approved for use with the voice client may result in poor audio quality, which results in poor recognition accuracy. See the List of Recommended Microphones.
      • If the user is dictating with nVoq.Mobile Voice:
        • The user could be covering the microphone with their hand. The microphone usually looks like a pinhole, and depending on the device it could be on the side, bottom, or top of the device. While dictating, the user should make sure that their hand is not covering or brushing up against the microphone pinhole.
        • The user could be in an area with poor connectivity. If they are in a location with a weak WiFi or cellular data connection, a notification should appear at the top of their screen to let them know (unless they have this setting disabled). Dictating in an area with a weak connection can affect dictation recognition.

           
  3. If the dictation audio is clear (no microphone issues, slurring, background noise, etc.), correct the dictation transcript to match what the user said.
    • This should be performed by someone familiar with clinical terminology. 
    • A nightly job will collect the corrections you make and apply it to the user’s profile overnight as sentence modeling. The sentence model tells the dictation engine to expect these words in this order. There is no need to send issues like this to nVoq Support. 
    • Make sure that any uncommon words that you correct are already in Vocabulary. Words in a sentence model that are not in vocabulary or the dictation topic will be skipped. If the word is uncommon, be sure to check both the user's Account Vocabulary and Organization Vocabulary for the term. 
    • See Review & Correct Detail: Correct a Dictation Transcript

       
  4. If correcting the problem dictations in Review & Correct does not resolve the issue, try adding an Account Substitution for common words or phrases that are returning incorrectly if they consistently return the same (incorrect) way.  
    • Rememebr that corrections made in Review & Correct create a sentence model that is applied to the user's profile over night, so be sure to test the issue the day after correcting problem dictations.
    • If the word or phrase is returning two different ways, it's OK to add two different substitutions to cover both incorrect returns.   
    • Make sure not to substitute something the user might actually dictate. Substitutions happen last in the dictation process, so they over-write what the engine thinks it heard with what you configure as the substitution EVERY TIME. For example, if every time the user dictates, "cabbage soup diet" the transcript says, "cabbage sweet diet," do NOT create a substitution to replace the word "soup" with "sweet" because the user would never be able to get the word "sweet" to return in a transcript after that. Instead, make a substitution that replaces the whole phrase "cabbage sweet diet" with "cabbage soup diet" since the user would not likely need to dictate "cabbage sweet diet" ever.
    • See Add Substitution

       
  5. If a word or phrases cannot be added as a substitution because it returns differently each time, try adding it as Account Vocabulary
    • Add the word or phrase first without any phonetic representation ("Sounds Like"). 
    • Small connecting words (like "a," "then," "the") should NEVER be added as vocabulary words. If these are a problem, address this using Sentence Modeling instead.
    • Adding common words or phrases to Vocabulary may make them more likely to return even when they are NOT dictated.
    • See Add Vocabulary

       
  6. If the above doesn't work to resolve the issue, try adding phonetic support (Sounds Like) to the term in the Account Vocabulary. 
    • This can be especially helpful if the person pronounces the word or phrase in a unique way. 
    • Keep one copy of the word without a Sounds Like and create a second copy of the term as another Account Vocabulary term and add the Sounds Like to that one. 
    • See Edit Vocabulary: Sounds Like

       
  7. If the user is still having issues with the word or phrase, try adding MORE sentence modeling. 
    • Upload a sentence modeling document to the user’s Account Sentence Modeling that includes 6-10 instances of the word or phrase in sentences that are similar to what will be dictated.
    • See Sentence Model Upload

       
  8. If none of the above works to resolve the issue, contact nVoq Support.
    • Be sure to provide the username of the person experiencing the issue and Dictation ID(s) of dictations in which the issue is occurring.