Playback Voice Control With Presence-Based Wake Word Activation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing playback devices struggle to efficiently manage multiple user profiles and voice assistant services, leading to increased computing load and resource inefficiency due to the concurrent execution of wake word detection engines for various voice assistants and media services.
Innovation Solution
Playback devices are configured to detect individual users and activate user profiles based on their presence, executing corresponding voice assistant wake word detection engines only when necessary, and deactivate profiles when users are no longer detected, thereby optimizing computing resources and memory usage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If playback devices execute wake word detection engines for multiple voice assistant services concurrently, then users can access multiple voice assistants, but computing load and resource consumption increase
Solution Approach 1:
The system dynamically activates and deactivates wake word detection engines based on user presence. When a user is detected, the corresponding voice assistant service is activated; when no user is present, the service is deactivated. This dynamic adjustment resolves the contradiction by providing multi-user support only when needed, reducing computing load during idle periods.
Solution Approach 2:
The system changes the operational state parameter of wake word detection engines from continuously active to conditionally active based on user presence detection. This parameter change allows the system to maintain versatility for multiple users while optimizing resource consumption by adjusting the activation state of processing engines.
2Adaptability or versatility
If playback devices maintain user profiles for multiple users, then user-specific preferences can be preserved, but memory usage increases
Solution Approach 1:
The system applies local quality by maintaining user profile data in a structured manner where each user's preferences and settings are stored separately. This allows the system to load only the necessary profile information into active memory when a specific user is detected, rather than keeping all user profiles fully loaded in memory simultaneously, thus managing memory usage efficiently while preserving user-specific capabilities.
Data Source
AI summary
Playback devices comprising a network interface, an optional speaker(s), and one or more processors are disclosed herein. In some embodiments, the playback device is configured to communicate with a computing system that stores configuration data corresponding to each of a plurality of users. The playback device detects one or more users near the playback device and retrieves user configuration data corresponding to each of the one or more detected users, and thereafter, uses the user configuration data of the one or more detected users to process voice commands, play media content, and/or perform other voice and/or media related functions.