Bone Conduction Noise Cancellation via Vibration Sensors

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional noise cancellation techniques struggle to achieve clear voice communications in dynamic and noisy environments, particularly where noises are not stationary or known in advance.

Innovation Solution

A noise cancellation system utilizing wearable devices with vibration sensors and microphones to detect and track speech signals, converting these signals into probabilistic distributions of linguistic representation sequences (PDLs), and then mapping them into full band Mel-Cepstral Features (MCEPs) for clear voice recovery.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If conventional noise cancellation techniques (beam forming, statistical noise reduction, frequency-bin filtering) are used, then stationary or known noises can be effectively cancelled, but dynamic and unknown noises in real-world environments cannot be reliably removed

Engineering Contradiction:
Improvenoise cancellation effectivenessVSAvoidadaptability to dynamic noisy environments
Core Design Contradiction:
ReliabilityVSAdaptability or versatility

Solution Approach 1:

The system performs preliminary action by capturing vibration signals from the user's body (chest, neck, or head) before the speech is affected by environmental noise. The vibration sensor detects the speech signal at the source through bone conduction and tissue transmission, isolating it from external noise contamination before any processing occurs.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system replaces conventional acoustic microphones that capture air-borne sound waves with vibration sensors that detect mechanical vibrations directly from the body. This substitution of detection mechanism (from acoustic to mechanical sensing) allows the system to bypass environmental noise and capture speech signals through physical vibration transmission through tissues.

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

2Measurement precision

If vibration sensors are used to detect speech signals through bone conduction, then clear speech can be captured in noisy environments, but the system requires enrollment phase to build speaker-specific models

Engineering Contradiction:
Improvespeech signal detection accuracyVSAvoidenrollment time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary action by conducting an enrollment phase where vibration signals are captured and used to build speaker-specific acoustic models. This preliminary modeling stores the relationship between the user's unique vocal tract characteristics and their speech patterns, enabling rapid and accurate speech recovery in subsequent noisy environments without requiring repeated enrollment.

Inventive Principle:
Principle #10Preliminary action

3Reliability

If deep learning-based noise cancellation using large amounts of data is used, then noise cancellation performance improves, but the system complexity and data requirements increase

Engineering Contradiction:
Improvenoise cancellation performanceVSAvoidsystem complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system extracts and utilizes the user's unique acoustic characteristics (such as vocal tract resonance, formant frequencies, and speech production patterns) captured during the enrollment phase. By focusing only on speaker-specific features rather than training on large general datasets, the system achieves high performance with minimal data requirements and reduced computational complexity.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The system applies local quality by tailoring the noise cancellation approach to each individual speaker's unique characteristics. Instead of using a generic noise cancellation model, the system adapts to the specific acoustic properties of each user's voice, achieving superior performance with personalized models built from minimal enrollment data.

Inventive Principle:
Principle #3Local quality

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 cancels noise and recovers clear voice communications in any noisy environment with high intelligibility, requiring only a few minutes of input speech during enrollment, and can be implemented in various configurations across wearable devices, computing hubs, or cloud servers.

Implementation Method 1

the vibration sensors include bone conduction sensors

Methodology Applied
Scientific EffectBone conduction:

Implementation Method 2

wearable devices with a vibration sensor and microphones to detect and track speech signals

Methodology Applied
Scientific EffectVibration sensing: Vibration

Data Source

PatentUS12277950B2Methods for clear call under noisy conditions
Publication Date: 2025.04.15 WENG FULIANG
  • US12277950B2 patent drawing
  • US12277950B2 patent drawing
  • US12277950B2 patent drawing

AI summary

This invention provides a new and improved voice communication system with high quality noise cancellation method and devices to overcome the limitations and difficulties encountered in conventional technologies. This invention discloses a noise cancellation apparatus that includes a vibration sensor and a microphone for receiving and transmitting voice signals as incoming speeches. The vibration sensor is applied to receive vibration signals corresponding to the voice signals for applying the vibration signals as reference signals for removing noise signals generated from environmental noises by converting vibration signals to intermediate PDL representation together with the speaker characteristics, mapping them into full band high quality clean acoustic representation, and synthesizing clear personal speech with characteristics identical to the original microphone speech without noises.