Speech-Dialog System for Web Table Information Access
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing speech-dialog systems cannot selectively interrogate and output information presented in tabular form on websites, limiting user access to such information, especially in scenarios where graphical user interfaces are not feasible, such as during a car journey.
Innovation Solution
A method and system that standardizes and edits information in tabular form for speech-dialog systems by assigning grammars to table elements and rows, enabling automatic conversion of internet-based applications into speech-accessible formats, allowing users to query table information using natural language.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If information is presented in tabular form on websites via graphical user interfaces, then information can be organized and displayed systematically, but users cannot access this information through speech during scenarios where graphical interfaces are not feasible (e.g., during car journeys)
Solution Approach 1:
The patent introduces a speech-dialog system as an intermediary between the user and the tabular information on websites. This system includes a speech recognition component that captures user speech, a processing component that interprets the speech in relation to table structures, and a speech synthesis component that outputs the retrieved information as spoken text, thereby enabling speech-based access to previously graphically-only information
Solution Approach 2:
The patent replaces the mechanical/visual interaction required by graphical user interfaces with acoustic interaction through speech recognition and synthesis. Instead of requiring users to visually navigate tables through mouse clicks or keyboard navigation, the system substitutes this mechanical interaction with voice-based queries and spoken responses
2Ease of operation
If a speech-dialog system is implemented to enable speech access to table information, then users can query information using natural language, but the system complexity increases requiring separate speech-dialog engines
Solution Approach 1:
The patent makes existing web table structures multi-functional by enabling them to serve both their original graphical display purpose and a new speech-dialog interface purpose. The same HTML table structures that display information visually are also made accessible through speech recognition and synthesis, allowing one system to fulfill multiple functions without requiring separate dedicated systems for each mode of access
Solution Approach 2:
The patent merges the speech recognition, speech synthesis, and table information retrieval functions into an integrated system that works with existing web infrastructure. Rather than creating completely separate speech-based systems, the approach combines speech processing capabilities with standard web table structures, allowing the same information infrastructure to serve both graphical and speech-based users
3Ease of operation
If standard speech recognition vocabulary is used for navigating websites, then basic navigation is enabled, but selective interrogation of tabular information is not possible
Solution Approach 1:
The patent segments the speech recognition approach into two distinct layers: a first level for general website navigation using standard vocabulary, and a second level for specific table information querying using domain-specific vocabulary. This segmentation allows each layer to be optimized for its specific purpose while working together to provide comprehensive access to both navigation and content information
Data Source
AI summary
In many application environments, it is desirable to provide voice access to tables on Internet pages, where the user asks a subject-related question in a natural language and receives an adequate answer from the table read out to him in a natural language. A method is disclosed for preparing information presented in a tabular form for a speech dialogue system so that the information of the table can be consulted in a user dialogue in a targeted manner.