Hearing Device Voice Control Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Hearing devices, such as hearing aids, face challenges in efficiently processing voice control commands due to limited computational power and battery life, which hinders effective keyword spotting and data transmission.
Innovation Solution
Incorporating an own voice detector into the hearing device to refine the output of the keyword spotting system, allowing for reduced false positives and improved power management by only activating voice control interfaces when the user's own voice is detected.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If keyword spotting and voice control processing are performed in the hearing device, then voice control functionality is improved, but computational power and battery life are depleted
Solution Approach 1:
The patent segments the voice control processing into two parts: keyword spotting is performed locally in the hearing device using minimal computational resources, while full speech recognition and processing are offloaded to an external device with greater computational power. This segmentation allows the hearing device to maintain voice control functionality while consuming significantly less battery power.
Solution Approach 2:
The patent introduces an intermediary architecture where the hearing device acts as a remote control for an external device. The hearing device detects keywords and transmits only relevant data segments to the external device, which then performs the computationally intensive speech recognition tasks. This intermediary approach enables voice control functionality while preserving battery life.
2Productivity
If continuous audio transmission to external device is performed, then processing capability is improved, but battery power is depleted
Solution Approach 1:
The patent implements periodic action by transmitting audio data only during specific periods when keywords are detected or when voice control is actively engaged. Instead of continuous transmission, the system periodically activates transmission based on detected speech events, thereby maintaining processing capability when needed while dramatically reducing overall power consumption during non-active periods.
Solution Approach 2:
The patent applies partial action by transmitting only the necessary portions of audio data (segments containing detected keywords or relevant speech portions) rather than continuous audio streams. This selective transmission of partial data maintains the external device's processing capability while minimizing the energy required for data transmission.
3Ease of operation
If wake-word detection is always active, then voice control responsiveness is improved, but power consumption increases
Solution Approach 1:
The patent applies dynamics by making wake-word detection configurable rather than always active. The system can dynamically adjust its sensitivity and activation state based on user preferences and environmental conditions. Users can enable or disable wake-word detection as needed, allowing the system to maintain responsiveness when required while conserving power during periods when voice control is not needed.
Data Source
AI summary
A hearing device, e.g. a hearing aid, is configured to be arranged at least partly on a user's head or at least partly implanted in a user's head. The hearing device comprises a) at least one input transducer for picking up an input sound signal from the environment and providing at least one electric input signal representing said input sound signal; b) a signal processor connected to the at least one input transducer, the signal processor being configured to analyze the electric input signal and to provide a transmit control signal in dependence thereof; c) a memory buffer, e.g. a cyclic buffer, for storing a current time segment of a certain duration of said at least one electric input signal, or a processed version thereof; and a transmitter for transmitting at least a part of said time segment, or a processed version thereof, to an external device in dependence of said transmit control signal.