Speech Command Substitution System for Acoustic Ambiguity Resolution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
User-defined speech commands can be acoustically similar to existing commands, leading to recognition ambiguities and user frustration, as users often struggle to find suitable substitutes that avoid confusion with existing commands.
Innovation Solution
A speech processing system that searches for potentially confusing terms and suggests synonyms or substitutes that are unlikely to be confused with existing commands, allowing users to accept or reject these suggestions, with the original command serving as a primary mechanism and the substitute as a secondary mechanism for triggering actions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a user defines a speech command that is convenient for them, then ease of operation is improved, but the command may be acoustically similar to existing commands causing recognition ambiguities
Solution Approach 1:
The system performs preliminary checking of the user-defined speech command against existing commands in the repository before finalizing it. The ambiguity detection engine proactively identifies potential acoustic similarities between the new command and existing commands, allowing the system to warn the user in advance and prevent recognition ambiguities before they occur
Solution Approach 2:
The system provides feedback to the user when a defined speech command has acoustic similarity to existing commands. The speech processing system generates warnings and suggestions for alternative commands, allowing the user to revise their command definition to avoid recognition ambiguities while maintaining ease of operation
2Reliability
If the system warns users about potentially ambiguous commands, then recognition accuracy is improved, but user frustration increases due to difficulty in finding suitable substitutes
Solution Approach 1:
The system acts as an intermediary by automatically generating substitute speech commands that are acoustically distinct from existing commands. When a user defines a potentially ambiguous command, the system provides pre-computed alternative commands that the user can easily select, eliminating the need for users to manually brainstorm alternatives and reducing frustration
Solution Approach 2:
The system creates copy variations of the user's intended command by generating phonetically similar but acoustically distinct alternatives. These substitute commands maintain the user's intended meaning while using different acoustic patterns that avoid conflicts with existing commands in the repository
3Reliability
If the system stores both original and substitute commands, then recognition accuracy is improved through backup mechanisms, but device complexity increases
Solution Approach 1:
The system merges the original user-defined command with its substitute alternatives into a unified command structure in the repository. Both commands are stored together and associated with the same functional action, allowing the speech recognition system to handle them as a coordinated set rather than separate independent commands, thereby managing complexity efficiently
Data Source
AI summary
A method for alleviating ambiguity issues of new user defined speech commands. An original command for a user-defined speech command can be received. It can then be determined if the original command is likely to be confused with a set of existing speech commands. When confusion is unlikely, the original command can be automatically stored. When confusion is likely, a substitute command that is unlikely to be confused with existing commands can be automatically determined. The substitute can be presented as an alternative to the original command and can be selectively stored as the user-defined speech command.