Digital Assistant Intercom Device Arbitration via Acoustic Fingerprinting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing digital assistant-based intercom systems face challenges in efficiently managing multiple device interactions and avoiding cross-talk, particularly in environments where multiple users and devices are scattered and not in a one-to-one mapping, leading to issues with acoustic transmission metrics and device-user mapping.
Innovation Solution
The implementation of a digital assistant system that uses acoustic fingerprints to determine the optimal device for transmitting messages, excluding devices with lower acoustic transmission metrics and preventing cross-talk by generating a device-user map based on acoustic features, allowing seamless intercom services without the need for continuous triggers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If multiple electronic devices provide audible representations of messages in an intercom system, then the system achieves greater versatility and user coverage, but cross-talk and acoustic interference increase
Solution Approach 1:
The patent applies local quality by assigning different arbitration outcomes to different devices based on their acoustic transmission metrics. Devices are evaluated individually using acoustic fingerprints and spatial relationships, allowing the system to selectively enable or exclude specific devices from providing audible representations based on their local acoustic characteristics rather than applying a uniform rule to all devices
Solution Approach 2:
The system implements feedback by continuously monitoring acoustic transmission metrics and using this information to dynamically adjust device participation in the intercom service. The arbitration process uses acoustic fingerprints and spatial relationship data to determine which devices should transmit messages, creating a closed-loop system that adapts to acoustic conditions and prevents cross-talk through informed decision-making
2Measurement precision
If acoustic fingerprint analysis is performed to determine optimal device transmission, then message transmission accuracy improves, but system complexity increases
Solution Approach 1:
The patent applies preliminary action by pre-computing and storing acoustic fingerprints and spatial relationship data for each device before intercom operations begin. This preparatory work allows the arbitration process to quickly reference pre-analyzed acoustic characteristics rather than performing complex real-time analysis during message transmission, thereby reducing operational complexity while maintaining high mapping accuracy
Solution Approach 2:
The system uses acoustic fingerprints as an intermediary representation that simplifies the complex task of device-user mapping. Instead of directly analyzing complex acoustic fields in real-time, the patent employs pre-extracted acoustic fingerprint features as mediators that capture essential acoustic characteristics in a manageable format, reducing computational complexity while preserving measurement precision
3Reliability
If devices are excluded based on acoustic transmission metrics, then cross-talk is reduced, but the number of active devices decreases
Solution Approach 1:
The patent applies parameter changes by dynamically adjusting the acoustic transmission metric thresholds that determine device inclusion or exclusion from the intercom service. Rather than using fixed criteria, the system adapts threshold parameters based on overall system acoustic conditions, ensuring that devices are excluded only when necessary for clarity while maximizing the number of participating devices under varying operational conditions
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
Enables efficient and clear communication among multiple users through accurate device-user mapping and acoustic fingerprint analysis, reducing cross-talk and enhancing the intercom experience by ensuring that messages are transmitted to the correct devices with the best acoustic reception.
Implementation Method 1
A second speech input may be received at the second electronic device. A third speech input may be received at the third electronic device. The second speech input includes a first reply to the message and a first acoustic fingerprint. The first acoustic fingerprint indicating a first acoustic transmission metric associated with a first spatial relationship between the second electronic device and a speaker of the first reply to the message.
Data Source
AI summary
Systems and processes for operating an intercom system via a digital assistant are provided. The intercom system is trigger-free, in that users communicate, in real-time, via devices without employing a trigger to speak. Acoustic fingerprints are employed to associate users with devices. Acoustic fingerprints include vector embeddings of speech input in an acoustic-feature vector space. Speech heard at multiple devices, as embedded in a fingerprint, may be clustered in the vector space, and the structure of the clusters is employed to associate users and devices. Based on the fingerprints, a device is mapped to a user, and the user employs that device to participate in a conversation, via the intercom service.