Speech Recognition System for Simultaneous Isolated and Connected Command Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing speech recognition systems in operating rooms require multiple voice commands to perform a single action and force unnatural speech patterns, leading to inefficiency and a need for extensive practice to use them effectively.
Innovation Solution
A speech recognition system that simultaneously supports both isolated and continuous speech commands, allowing for multiple commands to be recognized in a single utterance and accommodating traditional and non-traditional speech modes without reconfiguration, using a receiver, controller, language model, and software to convert speech inputs into computer-readable data and transmit active commands to devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional isolated speech recognition is used, then system reliability is maintained, but productivity decreases due to multiple commands required for single actions
Solution Approach 1:
The speech input is segmented into multiple isolated command components within a single utterance. The system divides the continuous speech stream into discrete recognizable commands, allowing multiple actions to be extracted and executed from one speech input, thereby improving productivity without sacrificing recognition reliability
Solution Approach 2:
The system dynamically adapts between isolated and connected speech recognition modes. It can switch between recognizing traditional isolated commands and newer continuous speech patterns, allowing the recognition approach to be optimized based on the specific input characteristics while maintaining both accuracy and efficiency
2Adaptability or versatility
If tree-structured command menu is implemented, then device control capability is enhanced, but loss of time increases due to multiple pause periods required
Solution Approach 1:
Multiple command levels from the tree-structured menu are merged into a single speech utterance. Instead of requiring separate commands for each menu level, the system combines multiple hierarchical commands into one continuous speech input, eliminating pause periods between commands while maintaining full device control capability
Solution Approach 2:
The system performs preliminary parsing and interpretation of multiple commands during a single speech capture window. By anticipating and preparing to recognize multiple commands simultaneously rather than sequentially, the system reduces the overall time required for command execution while maintaining the structured control hierarchy
3Measurement precision
If isolated speech commands are required, then measurement precision of command intent is improved, but ease of operation decreases due to unnatural speech patterns
Solution Approach 1:
The system is designed to handle multiple speech modes universally - both traditional isolated commands and more natural connected speech patterns. This multi-functionality allows the system to maintain precise command intent recognition while accommodating various speech styles, making the system easier to operate without sacrificing accuracy
Data Source
Figure 1
Figure 2
Figure 3A
AI summary
A system for operating one or more devices using speech input including a receiver for receiving a speech input, a controller in communication with said receiver, software executing on said controller for converting the speech input into computer-readable data, software executing on said controller for generating a table of active commands, the table including a portion of all valid commands of the system, software executing on said controller for identifying at least one active command represented by the data, and software executing on said controller for transmitting the active command to at least one device operable by the active command.