Event-Based Keyword Detector for Mobile Audio Power Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Voice-activated digital assistants on mobile devices face power consumption issues due to continuous operation of digital signal processors, making it impractical to deploy them on battery-operated devices without significant battery life impact.
Innovation Solution
Implementing an event-based keyword detector that uses a low-power component to analyze audio streams, activating the digital signal processor only when a keyword is detected, thereby reducing power consumption and enabling deployment on mobile devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a digital signal processor continuously processes audio streams to detect keywords, then keyword detection accuracy is improved, but power consumption increases significantly
Solution Approach 1:
The audio processing system is divided into two distinct segments: a low-power event detector that performs initial audio analysis and generates events, and a high-power digital signal processor that performs keyword detection only when events are detected. This segmentation allows the system to maintain keyword detection accuracy while dramatically reducing overall power consumption by keeping the DSP in sleep mode most of the time.
Solution Approach 2:
The event detector performs preliminary analysis of the audio stream before the digital signal processor engages. By detecting acoustic events in advance and generating corresponding events, the system prepares the keyword detector to activate only when necessary, avoiding continuous high-power operation while maintaining detection accuracy.
2Reliability
If the digital signal processor is activated continuously, then keyword detection reliability is improved, but battery life deteriorates
Solution Approach 1:
Instead of continuous operation, the digital signal processor is activated periodically and selectively based on events detected by the low-power event detector. The DSP transitions between active and sleep states, maintaining keyword detection reliability through event-triggered activation while extending battery life by minimizing high-power operation duration.
3Use of energy by moving object
If a low-power event detector is used to preprocess audio, then power consumption is reduced, but device complexity increases
Solution Approach 1:
An event detector serves as an intermediary component between the audio stream and the digital signal processor. This mediator analyzes audio characteristics and generates events that trigger DSP activation, enabling power reduction while managing system complexity through a specialized low-power component that bridges the gap between continuous audio monitoring and intermittent high-power processing.
Data Source
AI summary
In example implementations, a device is provided. The device includes a microphone, an event generator, a keyword detector, and a digital signal processor. The digital signal processor is in communication with the keyword detector. The microphone is to receive an audio signal. The event generator generates a pattern of events from the audio signal. The keyword detector detects a keyword based on the pattern of events generated by the event generator. In response to the keyword being detected, the digital signal processor is activated to analyze subsequent audio streams.