MaskClip: Detachable Clip-on Piezoelectric Sensing of Mask Surface Vibrations for Real-time Noise-Robust Speech Input

2025-05-04

AI Summary

To address severe speech quality degradation caused by mask-wearing, high computational overhead of existing solutions, and their compromises on hygiene and comfort, this paper proposes a contactless voice capture method based on piezoelectric sensing. A piezoelectric sensor is embedded in a detachable stainless-steel mask mount to directly transduce mechanical vibrations of the mask surface during speech, leveraging the mask itself as a natural acoustic filter for ambient noise suppression. The approach integrates vibration signal modeling, a lightweight speech enhancement algorithm, and human-centered hardware design. Evaluated under strong noise conditions, it achieves a 6.1% character error rate—significantly outperforming conventional microphones—and attains a subjective satisfaction score of 4.7/5.0 from 102 users. This work pioneers the transformation of masks into functional speech-sensing media, uniquely ensuring sterility, privacy, wearability compatibility, low power consumption, and robust performance.

Technology Category

• Natural Language Processing: Speech
• Machine Learning: Privacy
• Computer Vision: Biometrics, Face, Gesture & Pose

Application Category

• Security and Privacy: Privacy-enhancing technologies
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Masks are essential in medical settings and during infectious outbreaks but significantly impair speech communication, especially in environments with background noise. Existing solutions often require substantial computational resources or compromise hygiene and comfort. We propose a novel sensing approach that captures only the wearer's voice by detecting mask surface vibrations using a piezoelectric sensor. Our developed device, MaskClip, employs a stainless steel clip with an optimally positioned piezoelectric sensor to selectively capture speech vibrations while inherently filtering out ambient noise. Evaluation experiments demonstrated superior performance with a low Character Error Rate of 6.1% in noisy environments compared to conventional microphones. Subjective evaluations by 102 participants also showed high satisfaction scores. This approach shows promise for applications in settings where clear voice communication must be maintained while wearing protective equipment, such as medical facilities, cleanrooms, and industrial environments.

Problem

• Masks impair speech communication in noisy environments
• Existing solutions compromise hygiene, comfort, or efficiency
• Real-time noise-robust speech input for mask wearers needed

Innovation

• Piezoelectric sensor captures mask vibrations
• Stainless steel clip filters ambient noise
• Achieves low error rate in noise