Gaze-Based Dictation Intent Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Dictation systems face challenges in accurately determining when a user intends to dictate or edit text, leading to recognition mistakes and inefficiencies, as they struggle to differentiate between dictation and other user interactions.
Innovation Solution
The system uses gaze detection to determine whether a user is in dictation or editing mode, receiving and processing utterances based on the user's gaze direction to accurately interpret their intent and reduce the need for additional inputs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If dictation systems rely on speech recognition alone to determine user intent, then the system can operate with simpler input mechanisms, but it leads to recognition mistakes and inability to differentiate between dictation and other user interactions
Solution Approach 1:
The patent combines speech recognition with gaze detection to determine user intent. The system merges two different input modalities (audio and visual) to create a more reliable determination of whether the user intends to dictate or edit text, resolving the contradiction by improving reliability through combination rather than through a single complex mechanism
Solution Approach 2:
The system uses the gaze detection mechanism to serve multiple functions: determining dictation mode, determining editing mode, and differentiating between various user interactions. This multi-functional approach improves reliability without requiring separate specialized mechanisms for each function
2Reliability
If the system requires additional dialogue or inputs to confirm user intent, then it can reduce recognition mistakes, but it increases the number of user interactions and reduces efficiency
Solution Approach 1:
The system performs preliminary gaze detection to determine user intent before processing the speech input. By detecting gaze direction in advance, the system can pre-determine whether the user intends to dictate or edit, eliminating the need for additional confirmatory dialogue and improving overall efficiency while maintaining accuracy
3Reliability
If the system continuously monitors and processes additional user inputs to determine intent, then it can improve accuracy, but it consumes more battery power
Solution Approach 1:
The system uses partial monitoring by focusing gaze detection specifically on determining mode (dictation vs. editing) rather than continuously analyzing all aspects of user interaction. This selective approach maintains accuracy for the critical decision point while reducing overall processing load and battery consumption
Data Source
AI summary
Systems and processes for operating an intelligent dictation system based on gaze are provided. An example method includes, at an electronic device having one or more processors and memory, detecting a gaze of a user, determining based on the detected gaze of the user, whether to enter a dictation mode, and in accordance with a determination to enter the dictation mode: receiving an utterance; determining, based on the detected gaze of the user and the utterance, whether to enter an editing mode; and in accordance with a determination not to enter the editing mode, displaying a textual representation of the utterance on a screen of the electronic device.