Ear-Mountable Audio Voice Activity Detection via Dual Microphone Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing audio systems with noise cancellation techniques struggle to accurately detect voice activity in the ear canal of a user, especially when bone-conducted voice signals interfere with the adaptation process, leading to errors and false nulls.
Innovation Solution
An improved audio system and signal processing method that utilizes a voice activity detector to differentiate between user voice and ambient noise by analyzing the relationship between signals from two microphones, specifically the error microphone and the feed-forward microphone, and employing adaptive noise cancellation techniques to minimize interference.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If adaptive noise cancellation is used to minimize residual noise, then noise cancellation performance is improved, but false detections occur when users speak due to bone-conducted voice signals interfering with the adaptation process
Solution Approach 1:
The patent segments the voice detection function into a separate voice activity detector module that operates independently from the adaptive noise cancellation adaptation process. The VAD analyzes signals from both microphones to determine voice presence, and this information is used to control when adaptation should occur, preventing bone-conducted voice signals from interfering with the adaptation process
Solution Approach 2:
The voice activity detector acts as an intermediary between the microphones and the adaptive noise cancellation controller. It processes signals from both microphones, determines whether user voice is present, and controls the adaptation process accordingly, preventing false detections and interference during user speech
2Measurement precision
If the error microphone is placed close to the driver to detect ambient noise, then noise detection capability is improved, but bone-conducted voice signals from the user interfere with the signal
Solution Approach 1:
The system uses feedback from the voice activity detector to control the adaptive noise cancellation process. The VAD continuously monitors signals from both microphones and provides feedback about user voice presence, which then controls whether adaptation should proceed, preventing bone-conducted voice signals from interfering with the adaptation process
Solution Approach 2:
The system changes the operational parameters of the adaptive noise cancellation based on voice activity detection. When the VAD detects user voice, it modifies the adaptation process to prevent interference, effectively changing system behavior based on detected conditions
3Measurement precision
If the feed-forward microphone is placed outside the headphone to detect ambient sound, then ambient noise detection is improved, but the system cannot distinguish between user voice and third-party voice
Solution Approach 1:
The patent merges the signals from both the error microphone and feed-forward microphone in the voice activity detector. By analyzing the combined signals and their relationships, the system can distinguish user voice from third-party voice, enabling accurate control of the adaptive noise cancellation process
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
The system effectively detects user voice activity while minimizing false detections of third-party voices, thereby optimizing the adaptive noise cancellation process and maintaining effective noise reduction.
Implementation Method 1
an error microphone configured to sense sound being output from the speaker and ambient sound
Implementation Method 2
a feed-forward microphone configured to predominantly sense ambient sound
Implementation Method 3
when a headphone user is speaking, the signals at the microphones become mixed with bone conducted voice signals
Data Source
Figure 1~2
Figure 3
Figure 4~5
AI summary
An audio system for an ear mountable playback device (HP) comprises a speaker (SP), an error microphone (FB_MIC) predominantly sensing sound being output from the speaker (SP) and a feed-forward microphone (FF_MIC) predominantly sensing ambient sound. The audio system further comprises a voice activity detector (VAD) which is configured to record a feed-forward signal (FF) from the feed-forward microphone (FF_MIC). Furthermore, an error signal (ERR) is recorded from the error microphone (FB_MIC). A detection parameter is determined as a function of the feed-forward signal (FF) and the error signal (ERR). The detection parameter is monitored and a voice activity state is set depending on the detection parameter.