Silent speech detection using throat vibration with Ml and piezo sensors

Throat speech recognition is an efficient alternative to replace or substitute the old systems of speech recognition, especially where there is noise and where privacy is an issue, no opportunity of noise communication. Rather than using real world sensors or hardware installed, this study leans towards software method that makes use of the recorded or simulated data that are associated with the throat vibrations of the people to pretend that they are talking without sound. The data recorded with regards to the vibrations is initially converted using the Fast Fourier Transform to the frequency domain (FFT), so it is possible to identify relevant and meaningful spectral properties. These parameters can be used in the form of an learning in an Multilayer Perceptron (MLP) classifier, input non-linear patterns in learning which are supervised. After the system is able to effectively associate with proper training and learning specific words are spoken with particular vibrations. To assure privacy and data security of users, the process entirely is offline and has Command Line Interface (CLI) which represents the efficiency and practicability of human based on machine learning interaction through computers even in noise and safe communication.

Authors

Institutions

Publication Details

Journal
Noise & Vibration Worldwide
Published
2026-11-21
DOI
https://doi.org/10.1177/09574565261503880
Primary Topic
Speech Recognition and Synthesis
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Silent speech detection using throat vibration with Ml and piezo sensors

Mercy Paul Selvan, Grace Kanmani Prince, Mithila Murugan, Prathiksha Sathish Kumar et al.
Noise & Vibration Worldwide
Speech Recognition and Synthesis
article

Silent speech detection using throat vibration with Ml and piezo sensors

Mercy Paul Selvan, Grace Kanmani Prince, Mithila Murugan, Prathiksha Sathish Kumar, Usha Nandhini D, Santha Sheela AC
article en

Abstract

Throat speech recognition is an efficient alternative to replace or substitute the old systems of speech recognition, especially where there is noise and where privacy is an issue, no opportunity of noise communication. Rather than using real world sensors or hardware installed, this study leans towards software method that makes use of the recorded or simulated data that are associated with the throat vibrations of the people to pretend that they are talking without sound. The data recorded with regards to the vibrations is initially converted using the Fast Fourier Transform to the frequency domain (FFT), so it is possible to identify relevant and meaningful spectral properties. These parameters can be used in the form of an learning in an Multilayer Perceptron (MLP) classifier, input non-linear patterns in learning which are supervised. After the system is able to effectively associate with proper training and learning specific words are spoken with particular vibrations. To assure privacy and data security of users, the process entirely is offline and has Command Line Interface (CLI) which represents the efficiency and practicability of human based on machine learning interaction through computers even in noise and safe communication.

Noise & Vibration Worldwide
Sathyabama Institute of Science and Technology (IN)
Speech Recognition and Synthesis
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon
Silent speech detection using throat vibration with Ml and piezo sensors — Mercy Paul Selvan, Grace Kanmani Prince, et al. · Noise & Vibration Worldwide (2026) | TGRS Research Map | TGRS