Visual Display of Audible Voice Menu Options
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users interacting with automated voice systems face inefficiencies due to the need to listen to audibly presented options, which can be time-consuming and error-prone, especially when options are not pre-stored in a centralized database.
Innovation Solution
A system that visually displays options presented by automated voice systems using a centralized audible menu database, populated through crowdsourced information, allowing users to interact more efficiently and accurately by transcribing audibly presented options and storing them for future reference.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If users interact with automated voice systems by listening to audibly presented options, then the system maintains simplicity in presentation, but user interaction becomes time-consuming and error-prone
Solution Approach 1:
The patent creates a visual copy of the audible menu options by transcribing spoken words into text and displaying them on the screen. This allows users to see the same information that is being heard, enabling faster and more accurate interaction without changing the core voice system functionality.
Solution Approach 2:
The patent adds a visual dimension to the audio-only interaction model. By displaying transcribed text on the screen alongside or instead of audio playback, users can process information through both auditory and visual channels simultaneously, reducing interaction time and errors.
2Productivity
If a centralized audible menu database is used to store pre-transcribed options, then user interaction efficiency improves, but system complexity and infrastructure requirements increase
Solution Approach 1:
The patent performs menu transcription in advance and stores it in a centralized database. When users interact with the system, they receive pre-transcribed text rather than requiring real-time transcription, significantly improving interaction efficiency while distributing the processing load.
Solution Approach 2:
The system automatically transcribes and stores menu options from audio recordings without requiring manual intervention. The centralized database self-populates as users interact with various voice systems, reducing the need for manual database maintenance while building the infrastructure over time.
3Measurement precision
If real-time transcription of audible options is performed during user interaction, then visual display accuracy improves, but interaction time increases due to processing delay
Solution Approach 1:
The patent transcribes menu options in advance during system setup or idle periods, storing the transcribed text for immediate retrieval during user interactions. This eliminates real-time transcription delays while maintaining high accuracy through careful pre-processing.
Solution Approach 2:
The system dynamically adjusts its transcription approach based on availability of pre-transcribed data. When menu options are already in the database, it retrieves them instantly; when new options are encountered, it performs transcription and adds them to the database for future use, optimizing the balance between accuracy and speed.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Users' interaction performance with an automated voice system is improved, as is users' efficiency, by visually displaying options audibly presented by the automated voice system, thereby enabling users to interact with the system more quickly and accurately. Options can be obtained from a centralized audible menu database with the communicational identifier utilized to establish a communication connection with the automated voice system. The database is populated from crowdsourced information, provided when users establish communicational connections with portions of automated voice systems whose options have not yet been stored in the database, and then transcribe the options that are audibly presented by the automated voice system. Transcription of audibly presented options likewise serves as a double check to verify options already displayed. User interaction generates a subsequent communicational connection, with a different communicational identifier, to a different portion of the automated voice system, re-triggering the mechanisms.