Voice Selection Device with Guide Voice Cancellation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional voice selection devices struggle with voice recognition during the output of selection items with synthetic voice, limiting the ability to directly select items like music or images using voice commands.
Innovation Solution
A voice selecting device equipped with an output unit for guiding selection items, a voice recognition unit that can recognize instructions during or after the output of guide voice, and an interaction-control unit to select items, along with features like voice cancellation and input-waiting-time-length setting to enhance selection accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If voice recognition is performed during the output of guide voice, then voice selection capability is improved, but voice recognition accuracy deteriorates due to interference from synthetic voice
Solution Approach 1:
The patent extracts and removes the guide voice signal from the mixed audio input before voice recognition processing. The voice recognition unit receives only the user's voice command after the guide voice has been subtracted, thereby eliminating interference and maintaining high recognition accuracy while enabling voice selection during guide voice output.
Solution Approach 2:
The patent introduces a voice canceling unit as an intermediary component between the audio input and voice recognition unit. This mediator subtracts the guide voice signal from the composite audio stream, allowing the voice recognition system to process only the user's command without interference from the synthetic guide voice.
2Ease of operation
If voice recognition is performed during music or image playback, then direct voice selection is improved, but recognition accuracy deteriorates due to background noise
Solution Approach 1:
The patent extracts the user's voice command from the composite audio signal that contains music or other background sounds. The voice recognition unit processes only the extracted voice portion, effectively filtering out music and other non-voice sounds, thereby maintaining high recognition accuracy while enabling voice selection during media playback.
3Measurement precision
If the system waits for user input after guide voice output, then selection accuracy is improved, but response time deteriorates
Solution Approach 1:
The patent sets a predetermined time period immediately after guide voice output during which the system actively waits for and processes user voice input. This preliminary waiting period is built into the system's operation flow, allowing users to issue commands without delay while the system maintains readiness to recognize and process selections within this predetermined time window.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables users to accurately select items, including music and images, by raising a voice command during or after the output of guide voice, improving the usability of voice-controlled systems.
Implementation Method 1
the voice recognition unit has a voice canceling unit for subtracting the guide voice output by the output unit from the voice fed into the voice recognition unit
Data Source
AI summary
A selecting device according to voice includes output unit for outputting guide voice for guiding a selection item, voice recognition unit for recognizing a selection instruction for selecting the selection item that is issued during the output of the guide voice by output unit or within a certain time after the completion of the output, and interaction-control and result-selection unit for selecting the selection item instructed to be selected when voice recognition unit recognizes the selection instruction. When a voice for selecting a selection item is raised during the output of the guide voice by output unit or within the certain time after the completion of the output, voice recognition unit can select the selection item, and the selection item can be selected even during the output of the guide voice.