Voice Intelligence - Key Concepts

Language Operators — sometimes referred to as "operators" — use artificial intelligence and machine learning technology to turn transcripts into structured information using a variety of techniques. There are currently two categories of operators that can be used with Voice Intelligence.

• Prebuilt Language Operators — Prebuilt Language Operators have been created by Twilio or use third-party AI models. Twilio-made Operators are created, trained, and maintained by the Twilio team. These Operators are trained across a wide swath of data and typically map to pieces of information that are agnostic to use-case or industry. Prebuilt operators cannot be modified or made more specific.
• Custom Operators — These Operators are created and maintained by our customers. They are specific to an individual customer's use case and data. Custom Operators are text analysis operators — for example, they are keyword or phrase based — and can be used to spot phrases or classify transcripts.

See Supported Languages for details on Transcription languages that different Operators can support.

Operators perform a specific action on a conversation or a sentence within a conversation. There are five types of actions that an operator is able to perform.

Custom Operators are text-parsing based operators and support Classify and Phrase Matching.

To add a Custom Language Operator to your Services follow the steps below:

1. Navigate to the Language Operators tab on your Service.

2. Click Create Custom Operator.

3. Add the name of the operator and select Phrase Matching or Classify.

4. Create Phrase Sets. Each Phrase Set can have multiple words or phrases to extract from the transcript. For each phrase, you can select:
   A. Exact Match: Find exact words or phrases in transcript
   B. Fuzzy Match: Find words or phases in transcripts using machine learning techniques even if that match less than 100%

5. Once all the Phrase Sets are created, add the new Custom Language Operator to your Service. The next time a Transcript is created, the new Custom Language Operator results will be on the OperatorResults of the Transcript.

When there is audio that doesn't correspond to speech, or isn't recognized by Twilio's speech recognition engine, it will be labeled with a Non-Speech Tag. Currently, there are the following tags.