Multi-dimensional Voice Command Disambiguation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users face challenges in formulating effective search queries due to the vast amount of internet information, and existing voice command systems struggle with disambiguating voice commands in both recognition and intent dimensions, leading to ambiguity in intended actions.
Innovation Solution
A multi-dimensional disambiguation framework for voice commands that uses speech recognition to identify candidate terms and associate them with possible actions, providing users with a list of options to select the intended action, allowing for both implicit and explicit invocation of actions based on ambiguity values.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If speech recognition is used to identify candidate terms from voice commands, then the system can handle hands-free operation and improve user convenience, but ambiguity in term recognition and speaker intent increases
Solution Approach 1:
The disambiguation process is segmented into two distinct dimensions: quality of recognition dimension (matching sounds to candidate terms) and speaker intent dimension (determining possible actions). This segmentation allows the system to systematically address different sources of ambiguity separately, improving overall interpretation accuracy while maintaining hands-free operation convenience.
Solution Approach 2:
The patent introduces a second dimension of disambiguation beyond traditional speech recognition. Instead of only matching sounds to terms, the system adds the speaker intent dimension that analyzes possible actions associated with each candidate term. This dimensional expansion transforms the disambiguation process from one-dimensional term matching to two-dimensional term-action disambiguation, significantly reducing ambiguity.
2Measurement precision
If the system provides multiple candidate terms and actions for user selection, then interpretation accuracy improves, but the complexity of the system increases
Solution Approach 1:
The system performs preliminary disambiguation analysis by identifying candidate terms and their associated actions before presenting options to the user. The ambiguity values are calculated in advance, and the most likely interpretations are prepared and presented in a structured manner. This preliminary action reduces the computational burden during user interaction and simplifies the overall system complexity.
Solution Approach 2:
The system incorporates user feedback mechanisms where users can select from presented candidate terms and actions, or provide corrections. This feedback loop allows the system to learn from user preferences and improve future disambiguation accuracy. The feedback principle helps manage complexity by enabling the system to adapt to individual user patterns rather than requiring perfectly accurate automated disambiguation every time.
3Productivity
If ambiguity values are calculated for each action to determine implicit invocation, then automated execution accuracy improves, but computational requirements increase
Solution Approach 1:
The system uses ambiguity values as a key parameter to determine whether to automatically execute an action or present options to the user. By setting appropriate threshold values for ambiguity, the system can automatically execute high-confidence actions (improving productivity) while requiring user input only for ambiguous cases (reducing unnecessary computational energy consumption). This parameter-based decision-making efficiently balances automation and energy usage.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for processing voice commands. In one aspect, a method includes receiving an audio signal at a server, performing, by the server, speech recognition on the audio signal to identify one or more candidate terms that match one or more portions of the audio signal, identifying one or more possible intended actions for each candidate term, providing information for display on a client device, the information specifying the candidate terms and the actions for each candidate term, receiving from the client device an indication of an action selected by a user, where the action was selected from among the actions included in the provided information, and invoking the action selected by the user.