Vibration Motor Sound Sensor Using Back-EMF Signal Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current motion sensors in smartphones are limited in detecting meaningful speech and require vocabulary restrictions, while vibration motors in devices are not effectively utilized as sound sensors despite their potential for sound detection.
Innovation Solution
The use of vibration motors as sound sensors by leveraging reverse electromotive force and signal processing techniques such as spectral subtraction, energy localization, and harmonic reconstruction to decode human speech from low-bandwidth, distorted signals, allowing for the reconstruction of intelligible speech without machine learning or pattern recognition.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Use of energy by moving object
If motion sensors (accelerometers/gyroscopes) are used to detect sound signals, then continuous sound sensing is enabled with energy efficiency, but the vocabulary is limited to less than three keywords and meaningful speech detection is not achieved
Solution Approach 1:
The patent inverts the conventional use of vibration motors from actuators that generate vibration to sensors that detect vibration caused by sound waves. By applying reverse electromotive force, the vibration motor's movable mass responds to acoustic pressure changes, converting it into a functional microphone that preserves speech intelligibility while enabling continuous monitoring.
Solution Approach 2:
The patent changes the operational parameters of the vibration motor by applying reverse electromotive force, transforming it from a device that generates mechanical vibration to one that detects acoustic vibrations. This parameter change enables the device to function as a sound sensor with sufficient sensitivity for meaningful speech detection.
2Device complexity
If vibration motors are used as sound sensors, then the device complexity is reduced by using existing components, but the output signal is low-bandwidth and highly distorted
Solution Approach 1:
The patent converts the harmful distortion and low-bandwidth characteristics of the vibration motor output into beneficial features by applying signal processing techniques. The non-linear distortion is compensated for, and the limited bandwidth is optimized to capture the essential speech frequencies, transforming a poor-quality signal into usable speech data.
Solution Approach 2:
The patent replaces complex mechanical microphone structures with the simpler vibration motor mechanism. By using reverse electromotive force and digital signal processing, the mechanical simplicity of the vibration motor is leveraged to create a functional sound sensor with fewer moving parts and lower device complexity.
3Extent of automation
If pattern recognition algorithms are used on motion sensor signals, then sound detection is demonstrated, but the vocabulary is naturally limited to less than three keywords trained by a specific human speaker
Solution Approach 1:
The patent makes the vibration motor serve multiple functions: it acts as both a tactile actuator and a sound sensor. This multi-functionality eliminates the need for separate microphones in some applications and enables continuous speech monitoring with the same component, increasing adaptability across different use cases.
Solution Approach 2:
The patent implements feedback loops in the signal processing pipeline, where the detected vibration signals are continuously processed, refined, and compared against speech patterns. This feedback mechanism enables the system to adapt to different speakers and vocabulary, overcoming the limitation of fixed keyword recognition.
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
Enables the detection and decoding of human speech using vibration motors, potentially enhancing devices like wearables and smartphones, improving signal-to-noise ratio, and enabling new applications such as voice-controlled devices and eavesdropping capabilities.
Implementation Method 1
the same movable mass that causes the pulsation in such a motor (or other electromechanical device) may also respond to changes in air pressure
Data Source
AI summary
A device includes a coil and magnetic mass movable next to the coil in response to vibrations to generate a back electromotive force signal. An amplifier generates, from the back EMF signal, a vibration signal. A processing device converts the vibration signal to time-frequency domain signal as two-dimensional matrix of frequencies mapped against time slots. Pre-process voiced data of the time-frequency domain signal to generate a reduced-noise signal. Average signal values within a frequency window, and that exist at a first time slot, of the reduced-noise signal to generate a complex frequency coefficient. Shift the frequency window across the frequencies to generate multiple complex frequency coefficients that identify speech energy concentration. Replicate signal values at a fundamental frequency within the voiced data to multiple harmonic frequencies to generate an expanded voice source signal. Combine the speech energy concentration with the expanded voice source signal to recreate original speech.