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

Troubleshooting Dictation Recognition Issues (User Process)

  • Dark
    Light

Article Summary

If you are a user having issues with recognition of dictation transcripts, follow the steps below:  

You might need to add vocabulary or substitutions to your own account as part of this process.
If you do not have this ability, your administrator can do this for you. 

  

  1. Check your microphone.
    • If you're using nVoq.Mobile Voice:
      • Make sure you're not covering the microphone with your hand. The microphone usually looks like a pinhole, and depending on your device it could be on the side, bottom, or top of the device. While you're dictating, make sure your hand is not covering or brushing up against the microphone pinhole.
      • Make sure you're not in an area with poor connectivity. If you are in a location with a weak WiFi or cellular data connection, a notification should appear at the top of the screen to let you know (unless you have this setting disabled). Dictating in an area with a weak connection can affect dictation recognition.
        dictation_poor-network-connection-message
    • If you're using a desktop computer:
      • If you're using nVoq.Voice, be sure that you have the correct microphone selected on the Settings screen. If you're using an nVoq.Wireless Microphone with Voice, be sure that you have configured the Wireless Microphone to be your microphone (also on the Settings screen). See nVoq.Voice Settings.
      • Make sure your audio equipment is fully connected and working properly, and try restarting the computer. One issue that can occur when audio equipment is not fully connected and working properly is "jitter," which may sound like words are being skipped in the dictation recording.
        Here is an example of what jitter might sound like: 
      • Make sure you are using a recording device that is approved by nVoq for use with the voice client. 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 you are using a hand-held microphone, be sure that you stop recording before setting your microphone down so the recording doesn't pick up the sound of setting it down.
      • You may need to disable extraneous microphones. See Enable Microphone 

  2. Add uncommon words that are not returning correctly to your Vocabulary. 
    • This includes names of people, places, products, or even uncommon drug names.
      While nVoq makes every effort to protect PHI, we recommend that users of any speech recognition technology follow the HIPAA minimum necessary rule, which states, “Protected health information (PHI) should not be used or disclosed when it is not necessary to satisfy a particular purpose or carry out a function”.
      Not dictating PHI will not only meet these federal requirements under HIPAA, but will also reduce concerns regarding poor accuracy that result from unique name spellings. In most cases if you are dictating into an EHR you have already identified the patient and do not need to dictate PHI.
    • Common medical terms that are not returning correctly should be reported to your administrator.
    • If you don't have the ability to do this from your dictation client, your administrator can do this for you in nVoq.Administrator.

  3. Try adding a Substitution if common words or phrases are returning incorrectly if they consistently return the same (incorrect) way.
    • If the word or phrase returns the same way each time, you can create a substitution to replace the incorrect phrase with the correct one. If the phrase always returns one of two different ways, you can create two different substitutions to cover both incorrect returns.
    • Make sure not to create a substitution that will replace a word or phrase you actually DO want to see in a dictation at some point. For example, if every time you dictate, "cabbage soup diet" your transcript says, "cabbage sweet diet," do NOT create a substitution to replace the word "soup" with "sweet" because you will never be able to get the word "sweet" to return in a transcript. Instead, make a substitution that replaces the whole phrase "cabbage sweet diet" with "cabbage soup diet" since you would not likely need to dictate "cabbage sweet diet" ever.
    • If you don't have the ability to do this from your dictation client, your administrator can do this for you in nVoq.Administrator.

  4. If words or phrases cannot be corrected with a substitution because they return differently each time, try adding the problem word or phrase to your Vocabulary.
    • Add the word or phrase first without any phonetic representation ("Sounds Like") at first.  
    • Small connecting words (like "a," "then," "the") should NEVER be added as vocabulary words. If these are a problem for you, contact your administrator about addressing this using sentence modeling.
    • Adding common words or phrases to Vocabulary may make them more likely to return even when you don't say them. 
    • If you don't have the ability to do this from your dictation client, your administrator can do this for you in nVoq.Administrator.
    • See also: Vocabulary Not Recognized

  5. If adding the word or phrase to vocabulary is still not working, try adding phonetic support ("Sounds Like") for the term in Vocabulary. 
    • Keep one copy of the word without a Sounds Like and create a second copy of the term as another Vocabulary term and add the Sounds Like to that one. 
    • If you don't have the ability to do this from your dictation client, your administrator can do this for you in nVoq.Administrator.

  6. If none of the above resolves the issue, contact your administrator for further assistance.