Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Perceiving Loudness, Pitch, and Location

Perceiving Loudness, Pitch, and Location

The human brain perceives pitch through two primary mechanisms reflected in place theory and frequency theory. Each mechanism describes how sound waves are interpreted as specific pitches by the brain, offering insights into the intricate processes of auditory perception.
Place theory, or place coding, suggests that different pitches are heard because various sound waves activate specific locations along the cochlea's basilar membrane. The brain determines the pitch of a sound by...

Downsampling

Downsampling

When considering a sampled sequence with zero values between sampling instants, one can replace it by taking every N-th value of the sequence. At these integer multiples of N, the original and sampled sequences coincide. This process, known as decimation, involves extracting every N-th sample from a sequence, thereby creating a more efficient sequence.
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...

The Cochlea

The Cochlea

The cochlea is a coiled structure in the inner ear that contains hair cells—the sensory receptors of the auditory system. Sound waves are transmitted to the cochlea by small bones attached to the eardrum called the ossicles, which vibrate the oval window that leads to the inner ear. This causes fluid in the chambers of the cochlea to move, vibrating the basilar membrane.

Upsampling

Upsampling

Managing signal sampling rates is essential in digital signal processing to maintain signal integrity. A decimated signal, characterized by a reduced frequency range due to its lower sampling rate, can be upsampled by inserting zeros between each sample. This upsampling process expands the original spectrum and introduces repeated spectral replicas at intervals dictated by the new Nyquist frequency. To refine this zero-inserted sequence, it is passed through a lowpass filter with a cutoff...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Passive heart-rate monitoring during smartphone use in everyday life.

Nature·2026

Same author

Insulin resistance prediction from wearables and routine blood biomarkers.

Nature·2026

Same author

A scalable framework for evaluating health language models.

NPJ digital medicine·2026

Same author

Evaluating the performance and acceptability of an artificial intelligence digital health exercise platform in females with and without axial spondyloarthritis: a phase I study.

Advances in rheumatology (London, England)·2026

Same author

Differential sensitivity of impedance plethysmography and photoplethysmography sensors to temperature-induced peripheral vasoconstriction.

Scientific reports·2026

Same author

One-stop strabismus digital diagnosis via AI-integrated skin-like and wearable "Eyelectronics".

Science advances·2026

Search research articles

Related Experiment Video

Updated: Aug 15, 2025

Sound Source Localization Testing in Single-sided Deafness Following Bone Conduction Intervention

Sound Source Localization Testing in Single-sided Deafness Following Bone Conduction Intervention

Published on: December 20, 2024

Enabling Real-Time On-Chip Audio Super Resolution for Bone-Conduction Microphones.

Yuang Li^1,2, Yuntao Wang¹, Xin Liu³

¹Key Laboratory of Pervasive Computing, Ministry of Education, Department of Commputer Science and Technology, Tsinghua University, Beijing 100084, China.

Sensors (Basel, Switzerland)

|January 8, 2023

Summary

This study introduces a real-time system for bone-conduction microphones (BCM) that enhances speech audio quality in noisy settings. The novel deep learning model, ATS-UNet, achieves high-fidelity audio on low-power devices.

Keywords:

audio super-resolution bone-conduction microphone convolutional neural network real-time system

More Related Videos

A Lightweight, Headphones-based System for Manipulating Auditory Feedback in Songbirds

A Lightweight, Headphones-based System for Manipulating Auditory Feedback in Songbirds

Published on: November 26, 2012

Author Spotlight: Advancements in Impedance Monitoring for Cochlear Implant Surgery

Author Spotlight: Advancements in Impedance Monitoring for Cochlear Implant Surgery

Published on: August 4, 2023

Related Experiment Videos

Last Updated: Aug 15, 2025

Sound Source Localization Testing in Single-sided Deafness Following Bone Conduction Intervention

Sound Source Localization Testing in Single-sided Deafness Following Bone Conduction Intervention

Published on: December 20, 2024

A Lightweight, Headphones-based System for Manipulating Auditory Feedback in Songbirds

A Lightweight, Headphones-based System for Manipulating Auditory Feedback in Songbirds

Published on: November 26, 2012

Author Spotlight: Advancements in Impedance Monitoring for Cochlear Implant Surgery

Author Spotlight: Advancements in Impedance Monitoring for Cochlear Implant Surgery

Published on: August 4, 2023

Area of Science:

Audio Signal Processing
Machine Learning
Embedded Systems

Background:

Air-conduction microphones struggle with speech audibility in noisy environments.
Bone-conduction microphones (BCM) offer noise robustness but have limited bandwidth.
Existing audio super-resolution methods are computationally intensive for low-power devices.

Purpose of the Study:

To develop the first real-time, on-chip speech audio super-resolution system for BCM.
To create a computationally efficient deep learning model for embedded audio enhancement.
To improve speech quality for BCM in challenging acoustic conditions.

Main Methods:

Compared lightweight deep learning models for audio super-resolution.
Developed the Audio Temporal Shift Module (ATSM) for the ATS-UNet model.
Quantized and deployed ATS-UNet on ARM micro-controller units for real-time embedded processing.

Main Results:

ATS-UNet demonstrated cost-efficiency by reducing network dimensionality while preserving temporal speech features.
The system achieved real-time inference speeds on Cortex-M7 microcontrollers.
The proposed method significantly improved speech quality compared to baseline BCM and noise-reduction algorithms.

Conclusions:

The developed real-time on-chip system effectively enhances BCM audio quality.
ATS-UNet offers a computationally efficient solution for embedded audio super-resolution.
Human listeners perceived significant speech quality improvements using the proposed system.