Satellite Microphones for Conference Room Speaker Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing video conferencing systems face limitations in accurately detecting the speaker and estimating distance due to false positives from sound source localization (SSL) errors and a short baseline, which are exacerbated by reflections in the room and the need for additional microphones.

Innovation Solution

The implementation of satellite microphone systems with LED emitters to determine precise locations, improve SSL performance, and enhance active speaker detection (ASD) by using phase and amplitude measurements, while also estimating camera zoom settings based on satellite microphone signals.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a base microphone array is positioned on a table for speaker detection, then the system can detect speakers in a conference room, but the baseline is too short to accurately estimate speaker distance

Engineering Contradiction:

Improvespeaker distance estimation accuracyVSAvoidmicrophone array configuration

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent extends the microphone array from a two-dimensional table-top configuration to a three-dimensional structure by adding satellite microphones at elevated positions. This vertical dimension expansion creates a longer baseline, enabling accurate distance estimation while maintaining system functionality.

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

Solution Approach 2:

The microphone system is divided into a base array on the table and separate satellite microphones positioned at different locations and heights. This segmentation allows each component to serve specific functions: the base array for initial detection and satellite microphones for distance estimation and verification.

Inventive Principle:

Principle #1Segmentation

2Reliability

If conventional SSL algorithms are used for sound source localization, then the system can identify speaker locations, but false positives occur due to room reflections

Engineering Contradiction:

Improvespeaker detection accuracyVSAvoidroom reflections

Core Design Contradiction:

ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The patent implements a feedback mechanism where satellite microphone signals are used to verify and correct base array SSL results. The system continuously compares detections from both arrays and uses the satellite information to eliminate false positives caused by reflections, improving overall reliability.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The satellite microphones act as intermediary verification elements between the base array and the final speaker detection. They provide additional acoustic measurements that mediate the verification process, helping to distinguish true speakers from reflection-induced false positives.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Measurement precision

If additional microphones are added to extend the baseline for distance estimation, then accuracy improves, but the system complexity increases

Engineering Contradiction:

Improvedistance estimation accuracyVSAvoidmicrophone array structure

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The satellite microphones serve multiple functions simultaneously: they extend the baseline for distance estimation, provide verification for speaker detection, and contribute to the three-dimensional acoustic field characterization. This multi-functionality reduces the need for separate dedicated components.

Inventive Principle:

Principle #6Universality (Multi-functionality)

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

Significantly improves the true positive rate of sound source localization, reduces false positives, and enhances speaker detection accuracy by extending the microphone array baseline and utilizing satellite microphones to refine zoom capabilities.

Implementation Method 1

using an LED emitter to determine the precise location of satellite microphones on a table

Methodology Applied

Scientific EffectLight emission from LED: Light Emitting Diode

Implementation Method 2

using a satellite microphone phase to improve the SSL performance, using a satellite microphone audio amplitude to improve the active speaker detector (ASD) performance

Methodology Applied

Scientific EffectAcoustic detection: Sound

Data Source

PatentUS9071895B2Satellite microphones for improved speaker detection and zoom

Publication Date: 2015.06.30 MICROSOFT TECHNOLOGY LICENSING LLC

AI summary

Architecture for exploiting satellite microphones and employing other techniques of conference room camera/microphone systems to significantly improve the true positive rate (reduce false positives) in sound source localization (SSL). Techniques for realizing the improvement include using an LED emitter to determine the precise location of the satellite microphones on a table, using the base SSL and external sounds to determine the approximate location of the satellite microphone on the table, using the satellite microphone phase to improve the SSL performance, using the satellite microphone amplitude to improve the active speaker detector (ASD) performance, and using the satellite microphones to estimate camera zoom.