Inaudible Tone Suppressing Assistant Audio Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In multi-assistant environments, automated assistants can inadvertently respond to commands intended for another user's device, leading to resource wastage and unintended actions, as they rely solely on audio detection without context awareness.
Innovation Solution
A computing device renders a detectable output that temporarily limits the processing of audio data by other devices, preventing invocation phrase detection and speech recognition, thereby designating itself as the sole responsive device to assistant commands, using inaudible frequencies or irregular waveforms.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If multiple assistant devices continuously monitor for audio commands, then user accessibility and responsiveness are improved, but computational resources and energy consumption increase due to redundant processing
Solution Approach 1:
The system performs preliminary actions by having devices render suppressive outputs before actual command processing occurs. When a device detects another device is rendering a suppressive output, it preemptively limits its own audio processing, preventing redundant computations before they consume resources.
Solution Approach 2:
The suppressive output acts as an intermediary signal between devices. Instead of direct continuous communication about processing states, devices use this intermediary signal to coordinate their processing behavior, allowing one device to claim exclusive processing rights without requiring complex negotiation protocols.
2Speed
If assistant devices process all audio data continuously, then response speed is improved, but network bandwidth and processing capacity are wasted on unintended commands
Solution Approach 1:
The system performs preliminary coordination by rendering suppressive outputs that preemptively prevent other devices from processing audio commands. This eliminates the need for subsequent cancellation operations and network communication to correct unintended actions, saving bandwidth and processing capacity.
Solution Approach 2:
The suppressive output serves as a preliminary anti-action against unintended command processing. By detecting that another device is claiming exclusive processing rights through the suppressive output, devices preemptively limit their own processing, preventing wasteful network transmissions and computations before they occur.
3Device complexity
If devices lack context awareness in multi-user environments, then device complexity is reduced, but adaptability to shared spaces deteriorates leading to accidental activations
Solution Approach 1:
The suppressive output functions as a simple intermediary mechanism that enables devices to communicate processing claims without complex context-aware systems. Each device simply renders this standardized signal when claiming exclusive processing rights, allowing multi-device coordination through a uniform, low-complexity protocol rather than analyzing user intent or environmental context.
Solution Approach 2:
The system changes the parameter of audio processing behavior based on the detection of suppressive outputs. When a device detects another device is rendering the suppressive output, it modifies its processing state from active to limited, allowing adaptability to shared environments through parameter modification rather than complex contextual analysis.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This solution effectively prevents accidental invocation of other automated assistants, conserving computational resources and reducing network bandwidth usage, ensuring that only the intended device responds to user commands.
Implementation Method 1
the output can be rendered in a way that does not distract user(s) in the environment, such as by rendering audible output with a frequency (or frequencies) that is greater than a maximum frequency that is audible by a human (e.g., frequency or frequencies greater than 20 kHz)
Data Source
AI summary
Implementations set forth herein relate providing and/or detecting an automated assistant suppressing output for limiting responsiveness of an automated assistant that is available via another computing device. The output can be rendered as an inaudible tone in an environment, in order to pre-emptively suppress responses from automated assistants that may detect a forthcoming spoken utterance from a user. Limiting responsiveness in this way can preserve computational resources in environments, such as vehicles, in which multiple users may be carrying devices that are capable of being invoked via a spoken utterance. For instance, pre-emptively limiting responsiveness of other automated assistants can eliminate interruptions at devices that may other be inadvertently invoked as a result of detecting certain spoken utterances.