Context-Aware Speech Routing System for Ambiguous Utterances
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current speech processing systems face challenges in accurately determining the appropriate actions to perform or applications to use for ambiguous spoken utterances due to limited access to relevant contextual data during initial utterance meaning determination, leading to inaccurate routing and inability to integrate new actions or data without modifying underlying natural language understanding (NLU) processing.
Innovation Solution
Implementing a context-aware routing system that segregates speech processing into domains and subdomains, using intra-domain routing with confidence providers and a contextual data management system to assess and manage contextual information for routing decisions, allowing for dynamic and user-specific routing based on available data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If speech processing systems use initial utterance meaning determination with limited contextual data, then processing speed is maintained, but routing accuracy deteriorates for ambiguous utterances
Solution Approach 1:
The system performs preliminary actions by collecting and storing contextual data (location, calendar events, sensor data, etc.) before the routing decision is made. The contextual data management system proactively gathers this information and makes it available to confidence providers, who then use it to assess routing confidence without adding significant processing delay to the main speech processing pipeline.
2Adaptability or versatility
If the system integrates new actions or contextual data sources, then system versatility improves, but complexity of underlying NLU processing increases
Solution Approach 1:
The system segments the speech processing architecture into distinct modular components: the core NLU processing, the contextual data management system, confidence providers, and routing decisions. This segmentation allows new actions and data sources to be integrated by adding or modifying specific modules (e.g., new confidence providers or contextual data sources) without requiring changes to the underlying NLU processing logic.
Solution Approach 2:
The contextual data management system acts as an intermediary layer between the core NLU processing and the routing decision-making process. This intermediary collects, manages, and provides contextual information to confidence providers, which then feed into routing decisions. This architecture allows new data sources and actions to be integrated through the intermediary without affecting the core NLU system.
3Measurement precision
If the system uses domain segregation with intra-domain routing, then routing precision for specific domains improves, but system complexity increases
Solution Approach 1:
The system divides the speech processing system into multiple domains (e.g., home automation, media playback, messaging) with each domain having its own subdomains and specialized processing. This segmentation enables more precise routing within specific domains by using domain-specific contextual data and confidence providers, while the overall system manages complexity through modular domain definitions and standardized routing mechanisms.
Data Source
AI summary
A speech processing system uses contextual data to determine the specific domains, subdomains, and applications appropriate for taking action in response to spoken commands and other utterances. The system can use signals and other contextual data associated with an utterance, such as location signals, content catalog data, data regarding historical usage patterns, data regarding content visually presented on a display screen of a computing device when an utterance was made, other data, or some combination thereof.