Conference Endpoint Spoken Command Modification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users often forget to use the wake-up phrase or phrases associated with third-party services when issuing spoken commands, leading to ignored or improperly processed commands in speech recognition systems.
Innovation Solution
The system modifies spoken commands by adding a wake-up phrase or a third-party service phrase before transmitting them to a speech recognition service, allowing users to issue commands without explicitly saying these phrases.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the speech recognition system requires users to use wake-up phrases and third-party service phrases, then the system can reliably identify and process commands, but users may forget to use these phrases leading to ignored or improperly processed commands
Solution Approach 1:
The system performs preliminary action by automatically adding the required wake-up phrase or third-party service phrase to the user's spoken command before processing. This pre-modification ensures the command meets the speech recognition system's requirements without requiring the user to remember and utter the specific trigger phrases, thus maintaining reliability while improving ease of operation.
2Ease of operation
If the system automatically modifies spoken commands by adding phrases, then user convenience is improved, but the system complexity increases
Solution Approach 1:
The system introduces an intermediary component that acts as a bridge between the user's spoken command and the speech recognition service. This intermediary automatically analyzes the command, determines what modifications are needed (such as adding wake-up phrases or third-party service identifiers), and performs the modifications before forwarding the command. This modular approach manages system complexity by isolating the modification logic in a dedicated intermediary layer.
Data Source
AI summary
A method includes obtaining, at a first conference endpoint device, spoken command data representing a spoken command detected by the first conference endpoint device during a teleconference between the first conference endpoint device and a second conference endpoint device. The method further includes generating modified spoken command data by inserting a spoken phrase into the spoken command. The method further includes transmitting the modified spoken command data to a natural language service.