Network Microphone Orientation Toggle Between Local and Cloud Voice

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Users are apprehensive about sending their voice data to cloud-based voice assistant services for privacy reasons, while cloud-based VASes offer more capabilities than local natural language units.

Innovation Solution

Network microphone devices toggle voice input processing between cloud-based VAS and local NLU modes based on physical orientation, enabling privacy protection and utilizing local processing when the device is in a certain orientation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If voice input processing is performed via cloud-based VAS, then more capabilities are available, but user privacy is compromised due to voice data being sent to the cloud

Engineering Contradiction:

ImprovecapabilityVSAvoidprivacy risk

Core Design Contradiction:

Adaptability or versatilityVSObject-affected harmful factors

Solution Approach 1:

The system dynamically switches between cloud-based VAS and local NLU processing modes based on real-time user input characteristics. The processor analyzes incoming voice data and automatically routes it to the appropriate processing destination, enabling the system to adapt its privacy posture and capability level according to the specific interaction context.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The voice processing functionality is segmented into two distinct pathways: cloud-based VAS processing for complex queries requiring extensive capabilities, and local NLU processing for simpler commands that prioritize privacy. This segmentation allows the system to selectively engage cloud services only when necessary, thereby balancing capability access with privacy protection.

Inventive Principle:

Principle #1Segmentation

2Object-affected harmful factors

If voice input processing is performed locally via NLU, then user privacy is protected, but processing capabilities are limited compared to cloud-based VAS

Engineering Contradiction:

Improveprivacy protectionVSAvoidprocessing capability

Core Design Contradiction:

Object-affected harmful factorsVSAdaptability or versatility

Solution Approach 1:

The local NLU acts as an intermediary layer between the user and the cloud-based VAS. It first processes voice inputs locally to handle simple commands and privacy-sensitive operations, and only forwards more complex queries to the cloud service. This intermediary approach filters traffic to minimize cloud dependency while maintaining access to advanced capabilities when needed.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system implements local processing capabilities that are optimized for specific types of voice commands and contexts. Rather than attempting to replicate full cloud capabilities locally, the NLU is tailored to efficiently handle particular query types, providing adequate functionality for common tasks while preserving privacy for local operations.

Inventive Principle:

Principle #3Local quality

3Measurement precision

If the system always uses cloud-based VAS, then processing accuracy is improved, but network dependency increases and local functionality is reduced

Engineering Contradiction:

Improveprocessing accuracyVSAvoidnetwork dependency

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system dynamically adjusts its processing architecture based on network availability, query complexity, and privacy requirements. Rather than maintaining a fixed cloud-dependent architecture, it flexibly transitions between local and cloud processing modes, reducing network dependency while maintaining accuracy for tasks that benefit from cloud-based analysis.

Inventive Principle:

Principle #15Dynamics

4Device complexity

If the system always uses local NLU, then network independence is achieved, but processing accuracy and capability are reduced

Engineering Contradiction:

Improvenetwork independenceVSAvoidprocessing accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The system segments voice processing tasks by complexity and type, routing simple, routine commands to the local NLU for quick, network-independent handling, while forwarding complex, ambiguous, or data-intensive queries to the cloud-based VAS. This segmentation enables the system to maintain network independence for common operations while accessing enhanced accuracy when needed.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS12374333B2VAS toggle based on device orientation

Publication Date: 2025.07.29 SONOS INC

AI summary

As noted above, example techniques relate to toggling a cloud-based VAS between enabled and disabled modes. An example implementation involves a NMD detecting that the housing is in a first orientation and enabling a first mode. Enabling the first mode includes disabling voice input processing via a cloud-based VAS and enabling local voice input processing. In the first mode, the NMD captures sound data associated with a first voice input and detects, via a local natural language unit, that the first voice input comprises sound data matching one or more keywords. The NMD determines an intent of the first voice input and performs a first command according to the determined intent. The NMD may detect that the housing is in a second orientation and enables the second mode. Enabling the second mode includes enabling voice input processing via the cloud-based VAS.