MuniMins uses voice recognition technology to automatically identify who is speaking in your meeting recordings. The system learns each speaker's voice over time, getting more accurate with every meeting you process.
How It Works
- You can confirm the speakers voice match in the top section for "Speaker Identification"
- When you save a speaker, MuniMins stores a voice profile for that speaker
- On the next meeting for the same board, MuniMins will look for voice matches and, after a few meetings, will automatically recognize a speaker
- Once speakers are recognized you can confirm them in new meetings to further improve the voice identification feature.
- A voice profile can be created for Board Members, Particpants and identified Guests.
Before a voice profile is created, MuniMins will use voice recognition combined with context clues to determine the speakers. Remember, MuniMins uses the audio only, so individuals who don't speak or aren't identified in the meeting recording won't appear.
This will show all the voices that were recognized during the meetings and are able to be used for training purposes. Speakers will also have a label to reflect if they have been idenitified as a Board Member, Guest or Participant in your organization.
Not all speakers in the meeting will have enough voice data for training, so this list will not be a full list of those who spoke at the meeting.
Speaker Identification Window
If a speaker name is identified it will be shown with one of two types of labels - confidence rating (Medium/High) or a Percentage Match rating. For each person identified you can play a sample of their voice and then press confirm to have MuniMins use the recording for voice training.
Before voice profiles are build you will see each speaker that the system has identified with a tag for "HIGH" or "MEDIUM" confidence.
In this instance the system idenfied "George Washington" with high confidence and recognized he was a board member. You can verify this by playing a voice sample and then click "Confirm" to tell the system to remember how this speaker sounds.
When speakers are identifed via their voice the system will show a % match, rather than a confidence score.
In this meeting the voice profile for John Hancock matched with a 91% score.
The Training Period
On average it will take the system 2-4 meetings to build a good voice profile. Each meeting has slightly different audio, or, perhaps a member is remote, and overall if there is greater variety in the voice it will take longer to train.
| Meetings Confirmed | What Happens |
|---|---|
| 1st meeting | No profiles exist. You manually assign every speaker. Profiles are created. |
| 2–4 meetings | System suggests matches but with medium confidence. You confirm to strengthen profiles. |
| 5+ meetings | High-confidence matches are auto-confirmed during processing. No manual step needed. |
To track the status of voice identifiacation for Board Members, Guests or Particpants, go to the respective management page. Next to each name is a column for voice profile.
In this example, George Washington has a "Strong" profile with 15 meetings where his voice was confirmed. Mr. Jefferson has only one, while Mr. Adams voice hasn't yet been confirmed in speaker training.
Tips for best results:
- Remember to confirm new speakers and new boards in the first meeting - this maximizes the data MuniMins has to idenify the speakers going forward.
- If the same person sits on multiple boards, their voice profile carries across — once they're confirmed on one board, MuniMins recognizes them on others.
- Audio quality matters. Recordings with clear, separated audio (individual microphones or a good conference mic) produce better profiles than a laptop mic in a large room.
- If a member is inconsistent about how they particpate (remote vs. in person), or meetings take place in different rooms or using different recording equiement, the voice profile will take longer to build.
What About New Members?
When a new board member or participant joins, they start with no voice profile — just like when you first set up MuniMins. After they speak in a few meetings and you confirm their identity, their profile builds up and they'll be recognized automatically going forward.
If a member leaves and is replaced, simply add the new member under Organization → Members. Their voice profile builds independently.
Frequently Asked Questions
Do I need a microphone for each speaker?
No. MuniMins works with a single recording source — even a camera at the back of the room. MuniMins recognizes speakers through voice identification, or, in cases where there is no voice profile match, context.
What if the system identifies someone incorrectly?
You can easily change the identification in the MuniMins verification interface by clicking on the speaker name and choosing a different speaker.
Can I reset a voice profile?
You can reset the voice profile by clicking the Reset Voice button on their respective member/guest/participant page.
How many speakers can MuniMIns track?
There is no predefined limit to the number of voice profiles your account can have. However, using the member, particpant and guest feature properly is key to getting the best results.