How MeetRecord identifies speakers

MeetRecord analyzes calls using advanced methods to determine who spoke and when. This information is used to calculate stats and is displayed on the call page, helping you navigate and focus on relevant parts of the call.

Dividing Calls into Speaker Segments

The first step in speaker identification is segmenting the call into parts, each associated with a single speaker. MeetRecord uses different approaches depending on the type of call:

1. Meeting Calls

• MeetRecord examines the participant list during the call to estimate who is present and when they speak.
• Refining Speaker Identification:
  • Since conferencing systems often introduce delays in speaker detection, MeetRecord applies a proprietary algorithm to refine speaker identification.
  • Voice fingerprinting to assign the right internal speakers

2. Telephony Calls

• MeetRecord uses diarization to separate the single channel into multiple tracks based on voice differences.
• Machine learning assigns tracks to the appropriate speaker.

Participant Identification Methods

MeetRecord identifies participants differently based on the type of call:

1. Conference Calls

• Joining Methods:
  • Via Computer: Participants often identify themselves with their full name or a nickname.
  • Via Dial-In: The conferencing system may display a partial or full phone number.
• Identification Process:
  • Matches participant names or phone numbers to the meeting invite.
  • Learns nicknames and phone numbers over time for better accuracy.
• Handling Multiple Speakers on One Device:
  • If several participants use one device, they appear as a single speaker track, identified by the person logged into the web conference or dialed in.

2. Dialer Calls

• Audio is merged into a single channel. MeetRecord:
  • Uses diarization to separate speakers.
  • Leverages machine learning and diarization to assign tracks to speakers.
  • Utilizes Voice Fingerprinting to improve accuracy when language or conditions vary.

Voice Fingerprint for Dialer Calls

Voice fingerprint is a feature for dialer calls that uses samples of previous recordings to identify the MeetRecord user. Here's how it works:

Opt-In Requirement:

• This feature must be enabled by the administrator and opted into by team members.
• Voice identification is only stored for subscribed users.

Sample Collection:

• Introduction and 30 seconds audio samples are used to build a voice profile.
• Samples are refreshed over time to maintain accuracy.

On-the-Fly Analytics:

• Samples are used to identify users in real time without permanently storing any data.
• Past unidentified calls can be revisited and analyzed using updated voice profiles.

Variable Conditions:

• The system adapts to new environments, telephony systems, or equipment, like different headsets.

Key Notes on Speaker Identification

• MeetRecord doesn’t limit the number of identified speakers, but identification depends on input from the conferencing system or telephony system.
• Participants who are silent or unidentified are excluded from detailed speaker tracks.
• For maximum accuracy, voice fingerprinting is recommended for dialer calls.

By leveraging MeetRecord’s robust speaker identification and analysis features, you gain deeper insights into your calls, helping you focus on the moments that matter most.