Microphone Control Based on Speech Direction Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Users often forget that their microphones are muted during teleconferencing or videoconferencing, leading to confusion and repeated speech at the beginning of meetings, as existing solutions do not effectively determine the user's intention to speak or automatically unmute the microphone.

Innovation Solution

A processor-based system that analyzes audio signals to determine whether the user is facing the microphone by analyzing spectral or frequency content, using machine learning models like FCNN or CNN, and automatically unmutes the microphone based on this determination, allowing intended speech to be captured and communicated.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If the microphone is kept muted by default to prevent unintended speech capture, then privacy and control are improved, but the user experience deteriorates when users forget they are muted and have to repeat themselves

Engineering Contradiction:
Improvemicrophone control reliabilityVSAvoidease of speech capture
Core Design Contradiction:
ReliabilityVSEase of operation

Solution Approach 1:

The system automatically detects when the user intends to speak by analyzing audio signals and spectral content, then automatically unmutes the microphone without requiring manual user action. This self-service mechanism resolves the contradiction by making the system proactive in managing the mute state based on detected user intent.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system continuously monitors audio input and provides feedback about the detected speech direction and user intent. When the user speaks while facing the microphone, the system detects this through spectral analysis and provides feedback by automatically unmuting, creating a closed-loop control system that adapts to user behavior.

Inventive Principle:
Principle #23Feedback

2Ease of operation

If manual mute control is used to give users control over their microphone state, then user control is improved, but the system cannot automatically detect user intent leading to repeated speech

Engineering Contradiction:
Improveuser controlVSAvoidtime for repeated speech
Core Design Contradiction:
Ease of operationVSLoss of time

Solution Approach 1:

The system performs preliminary analysis of audio signals and spectral content to detect user intent before the user actually needs to speak. By proactively identifying when the user intends to speak and automatically unmuting in advance, the system eliminates the need for users to repeat themselves, thus recovering lost time while maintaining automatic control.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent replaces the mechanical manual mute control system with an automated acoustic detection system. Instead of requiring users to manually toggle mute buttons, the system uses spectral analysis and machine learning models to detect speech direction and automatically manage the mute state, substituting manual mechanical control with intelligent automated control.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

3Measurement precision

If automated speech detection is implemented to detect user intent, then speech capture accuracy is improved, but device complexity increases due to additional processing requirements

Engineering Contradiction:
Improvespeech direction detection accuracyVSAvoidprocessing system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system introduces an intermediary layer of spectral analysis and feature extraction between the raw audio input and the final speech detection decision. This intermediary processing layer, which includes analyzing spectral content and using machine learning models, enables accurate speech direction detection while managing complexity through modular, staged processing rather than attempting direct complex analysis.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP3900315B1Microphone control based on speech direction
Publication Date: 2023.09.27 HEWLETT PACKARD DEVELOPMENT COMPANY LP
  • EP3900315B1 patent drawingFigure 1
  • EP3900315B1 patent drawingFigure 2A
  • EP3900315B1 patent drawingFigure 2B

AI summary

According to examples, an apparatus may include a processor and a non-transitory computer readable medium on which is stored instructions that the processor may execute to access an audio signal captured by a microphone of a user's speech while the microphone is in a muted state. The processor may also execute the instructions to analyze a spectral or frequency content of the accessed audio signal to determine whether the user was facing the microphone while the user spoke. In addition, based on a determination that the user was facing the microphone while the user spoke, the processor may execute the instructions to unmute the microphone.