Using Speech Tags and Phrases

Overview

This page describes how to use Speech Tags and Phrases with Speech Recognition and provides some advice for administrators on creating phrases and Speech Tags to better serve user requests for assistance.

Speech Tags and Phrases require that Speech Recognition be properly licensed AND that transcriptions be generated. 

Permissions Required

Users

All users can view found Speech Tags and Phrases. No additional permissions are required. However, Speech Recognition must be properly licensed. 

Administrators 

The Speech Tag Management Screen is only accessible if the Speech Recognition license is installed and the user role has the correct privileges granted, otherwise it is not visible in the Quality Management main menu. The role needed is SPEEECHREC_ADMIN, which should be assigned manually to the user(s) that will manage speech tags and speech phrases. By default, this role is assigned to the CC Manager role as part of the DEFAULT_CC_MANAGER.

Architecture

Transcriptions generated by the Speech Recognition engine are utilized to find phrases defined by users/administrators of Eleveo Quality Management. The transcription file is then processed by the Speech Recognition component to find the user's pre-defined speech phrases. The found phrases are then saved to the database and are displayed to users on the Conversation Explorer screen.

The order of the process is important to note: 

1. Speech Tags and Phrases are created by users within Eleveo Quality Management. (as described on this page)
2. The Speech Recognition service processes an audio recording. A transcript is generated.
3. The transcription file is then processed by the Speech Recognition component to find the user's pre-defined speech phrases. 
4. The found phrases are then saved to the database and are displayed to users on the Conversation Explorer screen.

How Does Phrase Detection Work (in Brief) 

To find speech phrases that have been pre-defined by the user, the system performs several steps.

The list of speech phrases is compared to the transcription of audio recordings for each channel. To do this the system:

1. 1. First splits each speech phrase into a list of words,
   2. then it compares the transcription of the recording with the first word from the list of Speech Phrases(Step a) until the words are matched. When a match happens, the system then attempts to match the whole speech phrase (Step a)within the transcription of the same channel. When there is a match, the system saves the speech phrase occurrence to the database. 
   3. Found phrases are displayed within the Conversation Explorer. 

Special Characters 

• Can I use Special Characters (like commas, periods, and question marks) when creating Speech Phrases?
  • Yes, the following special characters are supported !, -, +, ., ^, :, ,(comma), \, ?

Numbers

• Can numbers be found by speech tags?
  • Yes. Speech tags support alphanumeric characters. Speech tags support both numbers and words. (e.g. 20 min / twenty minutes). To ensure that both variants are found we recommend that you include multiple phrases when creating a new tag. 

Are phrases case (in)sensitive

• When I create phrases, do I need to use capitalization of sentences?

  • No, the algorithm is not case-sensitive.

Use of Contractions 

• How does the algorithm deal with the use of contractions (words), Such as it's vs it is?
  • At the moment, the algorithm supports exact match only, in other words it's is NOT equal to it is. We recommend that multiple phrases be added to cover all variations that may be used. 

Timestamps

• How does the system display the found phrase based on the timestamp? If there is an entire sentence as a phrase, then what is the timestamp?
  • The timestamp is calculated in the following way – The speech phrase start-time is equal to the segment start-time shifted by the number of seconds of the first word matched from the transcription, the same applies to the speech phrase end-time, E.g. it is equal to the segment end-time shifted by the seconds of the last word matched from transcription.

• How does the system determine the occurrence of the first word? Average? Last?
  • It takes the first matched occurrence.

When Does the System Scan for Phrases?

Phrase detection occurs once a transcription has been processed. If no transcription is available, then no Speech Tags/Phrases will be found. 

Re-Scan

Rescan is currently not supported. We are actively working to enable this feature. 

Limitations

Scripted Greeting - Exact matches are required when searching for a phrase – It may be necessary to prepare several variants of the desired speech phrase, in order to capture all variations that an agent may use. For example: "Hello. Thank you for calling our Company. You are speaking to [agent name]. How may I help you?" May not be stated exactly the same each time, and therefore the transcription will vary. The speech phrases must be an exact match with the transcription in order to be matched. We recommend that you prepare several variants of the desired speech phrase. 

Supported Languages –  Phrase spotting is supported for all languages supported by Speech Recognition.

How to Prepare Speech Tags and Phrases

Speech Recognition searches for targeted phrases called Speech Tags which are grouped according to specific categories that you, or another user with the appropriate permission, create.

• The first step is to create Speech Tags. This is done by inputting specific phrases to associate with each Speech Tag.
• As the system searches for an exact match we suggest that each Speech Phrase be short. This will ensure that the search terms are sufficiently unique to be found.
• Once created you can search for enabled phrases according to Speech Tag.

Working with the Speech Tags Tab

To open the Speech Tags screen click the Speech Tags item on the left side menu.

Creating a New Speech Tag

The Speech Tags screen displays a list of existing Speech Tags that were already created. Otherwise, the list will be empty. 

To create a new Speech Tag click on Add New.

Enter the tag name in the Speech Tag field and add the Phrases you want to be associated with this tag.

Then click on Save.

Setting an Icon for a Speech Tag

To make it easier to identify a particular Speech Tag you can give it a unique icon. This icon will appear next to any conversation in which Speech Recognition finds an enabled phrase associated with that Speech Tag.

You can set the icon when creating the tag or later, by clicking on the tag to open the editing menu.

Adding a New Phrase to a Speech Tag

To add new phrases to your Speech Tag, select the particular tag and click Add New next to Phrases. Then click on Save.

We suggest that each Speech Phrase be short. This will ensure that the search terms are sufficiently unique to be found.

Only exact matches will be found.

Editing a Speech Tag

To modify a speech tag, click on the particular tag and make the changes in the editing window on the right. You can perform the following actions:

• Add New – Add a new phrase; click Add New to create a new phrase.
  
• Edit the Speech Tag icon – Click the icon and select from the available options.
• Name – Edit the Speech Tag name, change the title in the Speech Tag field.
• Enabled – Enable/Disable a phrase, use the corresponding checkbox to enable or disable a phrase.
• Delete Phrase – Remove a phrase – click the trash icon next to the phrase you want to delete.
• Delete Speech Tag - click on the trash icon on the top.
• Click Save to save your changes.

Export Speech Tags 

You can export all or selected Speech Tags in an XML file that you can save, as well as import to other instances of Quality Management. 

• To export all your speech tags – ensure no speech tag row is selected/highlighted and click Export to export all the Speech Tags. 

• To export only selected speech tags – make a selection of the speech tags you want to export and click the Export button.

  

  Selection tip

  Use the standard keys on your keyboard to select multiple rows. E.g. press and hold the Ctrl key (⌘ Command key on Mac) and select various rows or if needed deselect previously selected rows. Alternatively, hold the Shift key ⇧ (⇧ on Mac) to select multiple consecutive rows. 

Import Speech Tags

To import speech tags you need to have a previously exported XML file as described in the above Export Speech Tags section. Then click the Import button and choose the respective XML file from your computer. 

Example Phrases

Here are some examples of phrases that you may want to associate with a Speech Tag: