The “Science and Technology” section of this week’s issue of The Economist a feature with the title: “Correct Me If I’m Wrong…” (may require a subscription) In it, the author describes a new user interface called Parakeet, developed by Ola Kristensson and Keith Vertanen, at the University of Cambridge’s Computer Laboratory. Its purpose is to enable mobile subscribers to use the touch screen to correct or improve upon the first-pass results of speech-to-text conversion services.
Parakeet does not represent any technological leap forward. The program displays text versions of utterances for which the recognition engine has the highest confidence levels while it simultaneously displays several other renderings which carry lower degrees of confidence, sort of a range of so-called “nBest” candidates. Users can then indicate their actual utterances by using their fingers on the keyboard.
The originator of a spoken message performs first level triage by making sure that the message that is transmitted reflects what was spoken with great accuracy. I think this should be incorporated as an option for every mobile speech application.
Categories: Articles
Claude Managed Agents and the Parts of CX Automation That Shouldn’t Last
Oracle’s Service Manager Workspace Hints at an AI Control Layer for Service Operations
The Proof-of-Value Scoreboard: Measuring What Matters for BPO AI
Zoom’s Next Act Runs Through CX