Voice Input Processing via User-Specific Library Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electronic devices face challenges in processing voice inputs efficiently due to large word libraries and resource-intensive processing requirements, especially when handling complex instructions, which can consume significant power and be inaccessible in dark environments or for visually impaired users.
Innovation Solution
The electronic device identifies the user and defines a subset of library terms based on user interests and preferences, reducing the number of words to compare with the received voice input, thereby streamlining the processing and resource usage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a large word library is used to process voice inputs, then the accuracy of voice command recognition is improved, but the processing time and resource consumption increase significantly
Solution Approach 1:
The patent segments the large word library into multiple subsets organized in a hierarchical structure. The processing system divides the comprehensive vocabulary into categories and subcategories, allowing voice inputs to be processed against smaller, more manageable subsets rather than the entire library at once. This segmentation maintains recognition accuracy by preserving all necessary words while reducing the computational burden of processing.
Solution Approach 2:
The patent implements preliminary action by pre-organizing the word library into structured subsets and pre-processing voice inputs through initial analysis stages. The system performs preliminary filtering and categorization of both the vocabulary and incoming voice commands, so that when full processing is required, the work has already been partially accomplished, reducing overall processing time.
2Measurement precision
If a large word library is used to process voice inputs, then the accuracy of voice command recognition is improved, but the resource consumption increases significantly
Solution Approach 1:
The patent segments the large word library into multiple subsets organized in a hierarchical structure. The processing system divides the comprehensive vocabulary into categories and subcategories, allowing voice inputs to be processed against smaller, more manageable subsets rather than the entire library at once. This segmentation maintains recognition accuracy by preserving all necessary words while reducing the computational burden of processing.
Solution Approach 2:
The patent applies partial action by processing only the necessary subset of words required for a given voice command rather than the entire library. The system determines the minimal required vocabulary subset based on the context and type of command being recognized, performing only the partial processing needed to achieve accurate recognition without the excess resource consumption of processing all available words.
3Adaptability or versatility
If the electronic device displays a menu with selectable options, then the user can access electronic device operations, but the user must look at the display which consumes power and is inaccessible in dark environments or for visually impaired users
Solution Approach 1:
The patent replaces the visual display interface with a voice-based acoustic interface. Instead of requiring the user to visually interact with a displayed menu through sight and manual selection, the system substitutes this mechanical/visual interaction with voice command recognition and acoustic feedback. This substitution eliminates the need for display backlighting and visual engagement, significantly reducing power consumption while maintaining full accessibility to device operations for users in dark environments or with visual impairments.
Data Source
AI summary
This is directed to processing voice inputs received by an electronic device, and more specifically to receiving a voice input and identifying the user providing the voice input. The voice input can be processed using a subset of words from a library used to identify the words or phrases of the voice input. The subset can be selected such that voice inputs provided by the user are more likely to include words from the subset. The subset of the library can be selected using any suitable approach, including based on the user's interests and words that relate to those interests. For example, the subset can include one or more words related to media items selected by the user for storage on the electronic device, names of the user's contacts, applications or processes used by the user, or any other words relating to the user's interactions with the device.