Skip to end of banner
Go to start of banner

Using transcription and analytics in player

Skip to end of metadata
Go to start of metadata

You are viewing an old version of this page. View the current version.

Compare with Current View Page History

« Previous Version 14 Current »

Overview

Organizations use Verint Financial Compliance's Analytics Search capabilities to reduce the time and effort required to find potential compliance issues within Conversations.  This guide will describe how to interact with the:

  • Speech Analytics Tab
  • Speech Transcription Tab

Additional information on the media player guide can be found here: Using the media player

Speech analytics tab

A new Speech Analytics Tab is available for the in focus conversation this includes the following information

Expandable Information
Description
Language SpokenLists the detected languages spoken during the conversation.
Sentiment Analysis

Lists the granular count of TCU sentiment within the conversation.

The numbers with the colored background represent the number of TCUs in the respective sentiment category for the recorded conversation.

Topics

Lists key topics spoken within a conversation, providing a quick summary of the audio file content.

This also includes a time stamp, highlighting at which point during the topic was detected. The timestamp is a hyperlink and will move the player to the appropriate point in the Wav File.

SummaryA 100-500 word summary of the call, automatically generated from the key points of the conversation.

Transcription tab

The transcription tab provides the following functionality

Feature
Description
Auto ScrollThe transcription will scroll, in synch with the audio and audio player.
Speaker Diarization

Identifies the number of speakers in an audio file and segments the transcript according to speaker identity. Speaker 1, Speaker 2 etc…

TCU SentimentEach diarized segment of transcribed text is given a color coding to infer the sentiment score for the transcribed segment.
ConfidenceWords with a dashed underline are words with a low confidence score.
Sentiment

The color bars on the left present the sentiment score of the TCU on a scale of 5 categories:

  • Red: very negative sentiment
  • Light red: negative sentiment
  • Gray: neutral sentiment
  • Light green: positive sentiment
  • Green: very positive sentiment

By moving the cursor over the color bar, the exact sentiment score value is displayed.





  • No labels