Concurrent Voice Assistant Switching via Dynamic Audio Access
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automated assistants require manual configuration changes to switch between different hotwords, leading to inefficient resource utilization and negative user experiences when attempting unsupported tasks.
Innovation Solution
Implementing a system that allows multiple automated assistants to listen for different hotwords concurrently, with control of microphones and speakers dynamically assigned to the active assistant, and suppressing or buffering notifications based on priority, to enable seamless switching without configuration changes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a single automated assistant is selected and configured, then resource utilization is optimized and processing is simplified, but the user cannot switch between different assistants without manual configuration changes and may experience negative user experience when attempting unsupported tasks
Solution Approach 1:
The system dynamically assigns microphone access and processing rights to different automated assistants based on real-time hotword detection, allowing the configuration to change automatically without manual user intervention. This enables seamless switching between assistants while maintaining optimal resource utilization at any given moment.
Solution Approach 2:
The client device is designed to support multiple automated assistants simultaneously, with each assistant having its own hotword and capability set. The system universally handles multiple assistants through a unified architecture that manages resource allocation, enabling users to access different assistant functionalities without manual reconfiguration.
2Adaptability or versatility
If multiple automated assistants are supported with different hotwords, then user experience is improved and task support is expanded, but resource utilization becomes inefficient when all assistants continuously monitor for hotwords
Solution Approach 1:
The system extracts and isolates hotword detection processing to dedicated components that can efficiently monitor for hotwords without requiring full assistant activation. When a hotword is detected, only the relevant assistant is fully activated, preventing unnecessary computational resource consumption from continuously running all assistant functions.
Solution Approach 2:
The system dynamically activates and deactivates assistant processing based on hotword detection events. Instead of continuously running all assistants, the system transitions from a low-power state where only hotword detection occurs to an active state where the specific assistant handles the user's request, optimizing resource consumption throughout the interaction cycle.
3Speed
If all automated assistants continuously access microphones and audio data, then response time to hotwords is minimized, but privacy is compromised and resource consumption increases
Solution Approach 1:
The system separates hotword detection from full audio processing and assistant activation. Only the minimal necessary audio processing for hotword detection is performed continuously, while full assistant functionality is activated only when needed. This extraction approach maintains fast hotword response times while minimizing privacy risks and resource consumption during inactive periods.
4Productivity
If manual configuration is required to select an automated assistant, then resource utilization is optimized for a single assistant, but ease of operation deteriorates due to complex settings menus and inability to switch assistants
Solution Approach 1:
The system provides self-service assistant switching through hotword-based activation. Users can switch between assistants by simply speaking the corresponding hotword, eliminating the need to manually navigate settings menus or configure system preferences. The system automatically manages the switching process, maintaining efficiency while dramatically improving ease of operation.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Techniques are described herein for concurrent voice assistants. A method includes: providing first and second automated assistants with access to one or more microphones; receiving, from the first automated assistant, an indication that the first automated assistant has initiated a first session, and in response: continuing providing, to the first automated assistant, access to the one or more microphones; discontinuing providing, to the second automated assistant, access to the one or more microphones; and preventing the second automated assistant from accessing one or more portions of an output audio data stream; receiving, from the first automated assistant, an indication that the first session has ended, and in response: continuing providing, to the first automated assistant, access to the one or more microphones; resuming providing, to the second automated assistant, access to the one or more microphones; and resuming providing, to the second automated assistant, the output audio data stream.