Selective Abort of Voice Input Processing for Latency Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Voice-based user interfaces in mobile and automotive applications face latency and connectivity issues due to the need for continuous online connectivity, as they rely on client-server architectures that require online processing, which can be unreliable and slow.
Innovation Solution
Implementing a method that allows voice-enabled electronic devices to selectively abort online processing of voice inputs when local processing can complete the action without online data, using a streaming architecture to dynamically build voice actions from digital audio signals, and aborting online processing when local completion is possible, thereby reducing latency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If online processing is used for voice inputs, then speech recognition and semantic analysis functionality is improved, but latency and connectivity requirements worsen
Solution Approach 1:
The patent segments voice processing into two independent paths: online processing for complex semantic analysis and local processing for simple voice actions. The system determines whether a voice input requires online processing or can be handled locally, thereby reducing latency for simple commands while maintaining accurate recognition for complex requests.
Solution Approach 2:
The system performs preliminary analysis of the voice input to determine if it can be processed locally before committing to online processing. This preliminary action allows the system to avoid online processing latency for simple voice actions by identifying them early in the processing pipeline.
2Adaptability or versatility
If online processing is used for voice inputs, then complex semantic analysis is improved, but device connectivity requirements worsen
Solution Approach 1:
The patent segments processing capabilities into online and local components, allowing the device to operate independently of continuous connectivity. Simple voice actions are handled locally without requiring network connection, while complex semantic analysis utilizes online resources when available, thereby improving reliability.
Solution Approach 2:
The device is equipped with local processing capabilities that allow it to service simple voice actions independently without external assistance. This self-service capability ensures the device remains functional and reliable even when online connectivity is unavailable.
3Loss of time
If online processing is aborted early, then latency is reduced, but processing accuracy may worsen
Solution Approach 1:
The patent implements dynamic processing where the system continuously monitors the voice input stream and determines the appropriate processing path in real-time. This dynamic approach allows early abort of online processing when local handling is sufficient, reducing latency while maintaining accuracy through adaptive decision-making.
Solution Approach 2:
The system incorporates feedback mechanisms that monitor the progress of voice processing and determine whether local processing can achieve the required accuracy. This feedback loop allows the system to confidently abort online processing early when local processing is sufficient, maintaining accuracy while minimizing latency.
Data Source
Figure 1~2
Figure 3
Figure 4
AI summary
Online processing of a voice input directed to a voice-enabled electronic device is selectively aborted whenever it is determined that a voice input directed to the voice-enabled electronic device can be successfully processed locally by the device. Doing so may in some instances reduce the latency of responding to a voice input.