Distributed Voice Assistant Selection for Low-Latency Media Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing remote control devices face challenges in efficiently processing voice commands due to background noise, increased power consumption, reliance on single digital assistants, and high latency when sending voice inputs to cloud services, leading to decreased user satisfaction and increased costs.
Innovation Solution
Distribute speech recognition between a remote control device and a cloud-based voice platform, utilizing a local processor for initial voice command analysis and selecting the appropriate digital assistant based on trigger words, with preprocessing to reduce network usage and power consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If voice input is continuously streamed to cloud service for processing, then speech recognition accuracy is improved, but network consumption increases
Solution Approach 1:
The patent segments speech processing into two parts: local preprocessing (noise filtering, feature extraction) and cloud-based recognition. This segmentation allows the device to handle basic processing locally, reducing the amount of data that needs to be transmitted to the cloud, thereby improving speech recognition accuracy while reducing network consumption.
Solution Approach 2:
The patent applies preliminary action by performing voice activity detection and basic noise filtering locally before sending data to the cloud. This preprocessing step prepares the data in advance, ensuring that only relevant audio segments are transmitted, which improves recognition accuracy while minimizing network usage.
2Device complexity
If cloud service is used for voice processing, then device processing requirements are reduced, but response time increases due to network latency
Solution Approach 1:
The patent segments processing tasks by keeping simple, low-latency functions (voice activity detection, basic filtering) on the device and sending only essential data to the cloud. This segmentation enables the device to provide immediate feedback for simple operations while still utilizing cloud resources for complex recognition tasks.
Solution Approach 2:
The patent introduces an intermediary layer of local processing that acts as a buffer between the user and the cloud service. This intermediary performs preliminary analysis and only transmits necessary data to the cloud, reducing the impact of network latency on overall response time.
3Loss of time
If local processing is performed on the remote control device, then response time is reduced, but power consumption increases
Solution Approach 1:
The patent applies partial action by performing only essential local processing (voice activity detection, basic noise filtering) rather than complete speech recognition. This partial local processing reduces response time for initial detection while keeping power consumption low by avoiding full-scale local AI processing.
4Adaptability or versatility
If audio responsive remote control is used, then voice command functionality is added, but background noise reduces recognition accuracy
Solution Approach 1:
The patent introduces noise filtering as an intermediary processing step between audio input and speech recognition. This intermediary layer removes background noise and enhances voice signals before they are sent to the recognition engine, thereby maintaining voice command functionality while improving recognition accuracy in noisy environments.
Data Source
AI summary
Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for providing voice control using multiple digital assistants. In some embodiments, a voice platform operates to receive a voice input from a user. The voice platform selects a digital assistant from a plurality of digital assistants based on a trigger word. The voice platform then generates an intent from the voice input using the selected digital assistant. The voice platform then transmits the intent to a media device for processing.