Adaptive In-Canal and External Microphones for Speech Capture
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing ear-worn devices face challenges in capturing high-fidelity speech, particularly whispered or sub-vocalized speech, and suffer from noise interference and privacy issues due to ambient sound pickup, while conventional noise cancellation methods often degrade quality or fail to adapt to dynamic environments.
Innovation Solution
An ear-worn device utilizing an in-canal microphone and an array of external microphones that dynamically switch between capture modes based on environmental noise and speech content, employing beamforming, noise cancellation, and adaptive equalization to enhance speech detection and privacy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If an external microphone is used to capture speech, then speech can be captured from the user's mouth, but ambient sound and unwanted acoustic interference are also picked up, compromising privacy and noise cancellation
Solution Approach 1:
The patent divides the audio capture function into two separate microphones: an external microphone for capturing speech and an in-canal microphone for capturing bone-conducted speech and ambient noise. This segmentation allows the system to process and cancel ambient noise more effectively while preserving speech quality.
Solution Approach 2:
The in-canal microphone acts as an intermediary that captures bone-conducted speech vibrations directly from the skull, providing an alternative audio path that is less susceptible to ambient noise interference. This intermediary capture method complements the external microphone by providing a cleaner speech signal in noisy environments.
2Object-affected harmful factors
If an in-ear canal microphone is used to reduce ambient noise, then privacy and noise isolation are improved, but speech fidelity and full-spectrum capture are degraded
Solution Approach 1:
The patent merges the signals from both the external microphone and the in-canal microphone through processing that combines air-conducted speech (from external mic) with bone-conducted speech (from in-canal mic). This merging leverages the strengths of both microphones to achieve both noise isolation and speech fidelity.
Solution Approach 2:
The audio system uses a composite approach by combining two different audio capture pathways (air conduction and bone conduction) into a unified speech recognition system. This composite method allows the system to benefit from both the noise isolation of bone conduction and the full-spectrum capture of air conduction.
3Object-affected harmful factors
If the ear canal is fully occluded to isolate external noise, then noise isolation is improved, but internal body noise and vibrations are amplified, causing discomfort and distorted self-perception
Solution Approach 1:
The in-canal microphone provides feedback about internal body noises and vibrations to the processing system, which then uses this information to actively cancel or reduce these unwanted internal sounds. This feedback loop allows the system to distinguish between desired speech signals and unwanted internal body noises.
Solution Approach 2:
The patent converts the harmful effect of internal body noise amplification into a benefit by using the in-canal microphone to capture these internal sounds and then using signal processing to cancel them out. The very occlusion that causes internal noise amplification also enables the microphone to capture these sounds for subsequent cancellation.
4Measurement precision
If standard voice activity detection is used, then normal-volume speech is detected accurately, but whispered or sub-vocalized speech is missed due to low amplitude below detection thresholds
Solution Approach 1:
The patent changes the detection parameters by using bone conduction as an alternative transmission path for speech signals. Bone-conducted vibrations have different amplitude characteristics than air-conducted sound, allowing the system to detect whispered or sub-vocalized speech that would be below the detection threshold of conventional air-conduction microphones.
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
Improves voice activity detection, captures high-fidelity speech, and ensures privacy by minimizing sound leakage, adapting to various noise conditions and enhancing speech recognition accuracy.
Implementation Method 1
An in-canal microphone may suffer from limited fidelity or have difficulty capturing a robust full-spectrum speech signal
Implementation Method 2
perform beamforming to focus the array of microphones on the user's mouth
Implementation Method 3
Vibrations from speaking, chewing, or movement can resonate within the sealed ear canal, causing discomfort
Data Source
AI summary
Utilizing in-canal microphones and other microphones in wearable devices is described. One embodiment is an ear-worn device that includes an in-canal microphone configured to capture sounds in an ear canal and an array of microphones configured to capture external sounds. The ear-worn device may utilize the in-canal microphone to determine if the user is actively speaking. Upon such a determination, the ear-worn device may turn on the array of microphones to capture the user's voice and perform beamforming to focus the array of microphones on the user's mouth. Such speech can then be processed and provided to an artificial intelligence agent. The ear-worn device may switch between using the in-canal microphone and the array of microphones to capture the user's voice depending on environmental noise, the context of the user, and the voice content. The ear-worn device may also blend captures from the in-canal microphone and the array of microphones.