Speech Recognition for Localized Content via Knowledge Base Updates
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current speech recognition systems face challenges in efficiently processing speech commands for localized content, particularly in identifying available television channels and content, due to varying channel detection and access to over-the-air broadcasts and stored content across different devices.
Innovation Solution
A natural language processing system that generates and stores program data associated with localized content, including channel and content information, to improve speech recognition by updating a knowledge base and configuring an entity resolution component, allowing for accurate interpretation of voice commands based on detected channels and accessible content.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If speech recognition systems process speech commands for localized content, then speech processing accuracy is improved, but device complexity increases due to channel detection and content accessibility requirements
Solution Approach 1:
The patent introduces a content provider as an intermediary component that manages channel detection and content accessibility information. This mediator collects localized content data from multiple sources and provides it to the speech recognition system, allowing accurate speech processing without requiring the speech system itself to handle complex channel detection and content availability checks.
Solution Approach 2:
The system divides the complex task of localized content processing into separate functional modules: a content provider that handles channel detection and content accessibility, and a speech recognition system that processes speech commands using the content information. This segmentation allows each component to focus on specific functions, improving overall accuracy while managing complexity.
2Measurement precision
If the system determines availability and accessibility of channels and content across different devices, then speech command accuracy is improved, but processing time increases
Solution Approach 1:
The content provider performs channel detection and content accessibility determination in advance, before speech recognition is needed. By pre-gathering and storing localized content information about available channels and their accessibility across devices, the system eliminates the need for real-time content availability checks during speech processing, thus improving accuracy without adding processing time.
3Reliability
If the system stores and processes program data associated with localized content, then speech recognition reliability is improved, but memory and storage requirements increase
Solution Approach 1:
The system stores and processes only the specific localized content information relevant to the current context and device, rather than maintaining comprehensive databases of all possible content. The content provider collects and stores program data only for channels and content that are actually accessible to the user's device, reducing storage requirements while maintaining high speech recognition reliability for relevant content.
Data Source
AI summary
A system capable of generating and storing program data associated with localized content, such as over-the-air television broadcasts. The system may update a knowledge base with the program data to improve natural language understanding (NLU) processing associated with the localized content. For example, a voice enabled device may receive a voice command and the system may perform NLU processing to interpret the voice command, determine content based on the program data and send an instruction to an output device to output the content. The program data may include information about localized content such as channels detected by the output device and/or content broadcast on the channels, including information about an output device, a channel number, call sign, station name, signal strength, etc. associated with a detected channel, and/or a program name, genre, actors, directors, producers, etc. associated with content broadcast on the channel or stored in a local storage device.