Parameterizable Speech Grammar for Secure Voice Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current speech recognition systems, particularly in VoiceXML, have limited parameterization options for configuring grammars, which restricts the ability to specify complex or custom input constraints, leading to inefficiencies and potential security risks when using scripting engines for semantic interpretation.
Innovation Solution
Implementing parameterizable grammars in a modified SRGS syntax that allows for richer and more complex grammar specifications, enabling the use of parameterized rules without relying on separate scripting engines like ECMAScript or JavaScript, thereby improving runtime performance and reducing latency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If scripting engines (ECMAScript/JavaScript) are used for semantic interpretation, then grammar configuration flexibility is improved, but system security is worsened and runtime performance decreases
Solution Approach 1:
The patent extracts the semantic interpretation functionality from scripting engines and implements it natively within the speech recognition system. By removing the dependency on external scripting engines, the system eliminates security vulnerabilities associated with script execution while maintaining grammar configuration flexibility through built-in parameter handling capabilities.
Solution Approach 2:
The patent replaces the mechanical system of scripting engines with a native parameter-based grammar configuration system. Instead of using ECMAScript/JavaScript for semantic interpretation, the system uses dedicated parameter structures and native processing mechanisms, achieving both improved security and performance.
2Adaptability or versatility
If scripting engines are used for semantic interpretation, then grammar configuration flexibility is improved, but runtime performance is worsened
Solution Approach 1:
The patent removes the overhead of scripting engine execution by extracting semantic interpretation to native system processing. This eliminates the performance penalty associated with interpreting scripts at runtime, while grammar flexibility is maintained through parameterized grammar rules.
Solution Approach 2:
The patent substitutes the scripting engine execution model with a native parameter processing model. This replacement eliminates the interpretation overhead and achieves faster runtime performance through direct parameter-based grammar matching and semantic interpretation.
3Device complexity
If limited parameterization options are used in VoiceXML, then system complexity is reduced, but grammar specification capability is worsened
Solution Approach 1:
The patent introduces dynamic parameterization capabilities that allow grammar specifications to be flexibly configured without increasing overall system complexity. Parameters can be dynamically set and modified, enabling complex grammar patterns while maintaining a clean, manageable system architecture.
Solution Approach 2:
The patent extends parameterization options by introducing new parameters for grammar specification. This allows more expressive and flexible grammar definitions through additional parameters such as semantic tags, weights, and constraints, without fundamentally changing the system's core structure or increasing complexity.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method includes: loading, by a processor, a grammar specification defining at least one parameterizable grammar including a plurality of rules; setting, by the processor, an initial state of a grammar processor as a current state, the current state including parameters supplied to the rules; selecting, by the processor, a rule of the plurality of rules matching the parameters of the current state of the grammar processor; applying, by the processor, the selected rule to the audio and updating the current state; determining, by the processor, whether termination conditions have been met; in response to determining the termination conditions are not met, selecting, by the processor, from the plurality of rules in accordance with parameters of the updated state; and in response to determining the termination conditions are met, outputting, by the processor, a recognizer result of the current state.