Earbud Speech Estimation Using Bone Conduction Sensor
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Earbud headsets face challenges in speech capture due to their in-ear position, which limits microphone placement and occludes acoustic signals, making it difficult to differentiate user voice from surrounding noise, especially in wireless earbuds with limited battery power and form factor constraints.
Innovation Solution
A signal processing device and method using a bone conduction sensor to determine non-binary characteristics of speech, such as speech level or spectral envelope, to derive signal conditioning parameters for conditioning the microphone signal, enabling effective noise reduction and speech estimation without relying on voice activity detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Volume of moving object
If the earbud is positioned in the ear canal, then the form factor is compact and comfortable, but the acoustic signal path is occluded and microphone placement is constrained
Solution Approach 1:
The patent introduces a bone conduction sensor as an intermediary device to capture speech signals. Instead of relying solely on microphones that are blocked by the ear canal anatomy, the bone conduction sensor detects vibrations from the user's vocal cords through the bone structure, providing an alternative signal path that bypasses the occlusion problem while maintaining the compact in-ear form factor
2Reliability
If microphones are positioned widely apart for beam forming, then noise reduction performance improves, but the earbud geometry cannot accommodate such placement
Solution Approach 1:
The bone conduction sensor serves as a mediator that enables speech capture functionality equivalent to having widely-spaced microphones. By detecting bone vibrations directly, the system achieves reliable speech signal acquisition without needing to physically separate multiple microphones, thus maintaining the compact earbud geometry while achieving effective noise reduction through alternative signal processing paths
3Productivity
If voice activity detection is used for speech capture, then processing efficiency improves, but speech from other persons within the beam can corrupt the capture
Solution Approach 1:
The bone conduction sensor acts as a selective intermediary that captures only the user's own speech vibrations through bone conduction, inherently filtering out speech from other persons. This provides a more reliable speech capture mechanism compared to traditional voice activity detection on microphone signals, as the bone conduction path is specific to the user's own vocal vibrations, while still maintaining processing efficiency through direct signal acquisition
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
This approach improves speech quality by applying non-stationary noise reduction and conditioning the microphone signal based on bone conduction sensor data, enhancing speech capture and reducing noise interference in earbud headsets, particularly in wireless earbuds with limited power and form factor constraints.
Implementation Method 1
determine from the bone conduction sensor signal at least one characteristic of speech of a user of the earbud
Data Source
AI summary
Embodiments of the invention determine a speech estimate using a bone conduction sensor or accelerometer, without employing voice activity detection gating of speech estimation. Speech estimation is based either exclusively on the bone conduction signal, or is performed in combination with a microphone signal. The speech estimate is then used to condition an output signal of the microphone. There are multiple use cases for speech processing in audio devices.