Speech Interface Arbitration Using Context Across Multiple Devices
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In environments with multiple voice-enabled computing devices, traditional methods for selecting a device to respond to a user's voice command often fail to consider contextual information, leading to inappropriate device selection and potential duplicate processing of the same command.
Innovation Solution
A remote speech processing service employs arbitration techniques using contextual information, including signal-to-noise ratios, device states, and natural language understanding, to select the most appropriate device to respond to a voice command by analyzing metadata and audio signals from multiple devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional device selection methods are used in multi-device environments, then device selection is simple and fast, but device selection accuracy deteriorates leading to inappropriate device selection and duplicate processing
Solution Approach 1:
A remote speech processing service is introduced as an intermediary between multiple speech interface devices and the user. This service receives audio signals and metadata from multiple devices, performs arbitration to determine the most appropriate device for responding to the speech utterance, and coordinates the response. The intermediary handles the complexity of multi-device arbitration centrally, improving selection accuracy without requiring complex local processing on each device.
Solution Approach 2:
The system performs preliminary actions by collecting metadata and audio signals from multiple devices before making the device selection decision. The remote speech processing service receives and analyzes information from all candidate devices in advance, evaluating contextual factors such as device states, signal-to-noise ratios, and proximity to the user, thereby making an informed selection before the actual response is generated.
2Productivity
If multiple devices independently process voice commands, then each device can respond autonomously, but duplicate processing occurs and resource usage increases
Solution Approach 1:
The remote speech processing service implements a feedback mechanism where it receives information from multiple devices, determines the most appropriate device for response, and coordinates the actual response execution. This feedback loop ensures that only the selected device processes and responds to the speech utterance, preventing duplicate processing while maintaining the ability for multiple devices to monitor and participate in the arbitration process.
3Measurement precision
If contextual information is analyzed for device arbitration, then device selection accuracy improves, but processing time and computational load increase
Solution Approach 1:
The system applies partial action by selectively analyzing contextual information from multiple devices rather than processing all possible data from all devices equally. The remote speech processing service evaluates relevant contextual factors such as device states, signal-to-noise ratios, and user proximity to make an informed selection, performing only the necessary analysis required to determine the most appropriate responding device without exhaustive processing of all available data.
Data Source
AI summary
This disclosure describes, in part, context-driven device arbitration techniques to select a speech interface device from multiple speech interface devices to provide a response to a command included in a speech utterance of a user. In some examples, the context-driven arbitration techniques may include executing multiple pipeline instances to analyze audio signals and device metadata received from each of the multiple speech interface devices which detected the speech utterance. A remote speech processing service may execute the multiple pipeline instances and analyze the audio signals and/or metadata, at various stages of the pipeline instances, to determine which speech interface device is to respond to the speech utterance.