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

Search research articles

Related Experiment Video

Updated: Oct 11, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Sound source localization based on multi-task learning and image translation network.

Yifan Wu¹, Roshan Ayyalasomayajula¹, Michael J Bianco¹

¹University of California, San Diego, La Jolla, California 92093, USA.

The Journal of the Acoustical Society of America

|December 2, 2021

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by

Same author

A Multi-Head Attention Transformer Model for Wearable in Situ Fall Detection.

IEEE access : practical innovations, open solutions·2026

Same author

Continuous forecasting of range-dependent ocean sound speed field: Diffusion model meets multi-output Gaussian process.

The Journal of the Acoustical Society of America·2026

Same author

Sensor beampattern and equivalent aperture in a distributed acoustic sensing system.

The Journal of the Acoustical Society of America·2026

Same author

Hankel-FNO: Fast underwater acoustic charting via physics-encoded Fourier neural operator.

The Journal of the Acoustical Society of America·2025

Same author

Evaluating Gaussian processes for matched-field processing localization using minimum mean squared error criterion.

JASA express letters·2025

Same author

Differentiable physics for sound field reconstruction.

The Journal of the Acoustical Society of America·2025

Same journal

Reducing computational complexity in adaptive sound zones with online room impulse response estimation.

The Journal of the Acoustical Society of America·2026

Same journal

Small-sample unbiased linear coherence estimators for a complex Gaussian random process.

The Journal of the Acoustical Society of America·2026

Same journal

Automated detection and annotation of toothed-whale whistles using transformer-based instance segmentation.

The Journal of the Acoustical Society of America·2026

Same journal

Effect of temperature and concentration on the thermo-acoustic behavior of vitamin B5 (d-Panthenol) solutions in the presence of glycol additives.

The Journal of the Acoustical Society of America·2026

Same journal

The visome: Using cognitive networks to examine lip-reading errors in English words.

The Journal of the Acoustical Society of America·2026

Same journal

Resident subjective annoyance responses to combined road traffic and train-induced structure-borne noise: Effects of sound environment.

The Journal of the Acoustical Society of America·2026

See all related articles

This study introduces MTIT, a novel deep learning framework for sound source localization (SSL) indoors. MTIT accurately predicts sound source positions by addressing multipath effects and improving localization accuracy.

Area of Science:

Acoustics
Machine Learning
Signal Processing

Background:

Supervised learning methods for sound source localization (SSL) have demonstrated significant accuracy.
Accurate indoor sound source localization remains challenging due to factors like multipath propagation.

Purpose of the Study:

To present MTIT, a deep neural network (DNN) framework for indoor sound source localization using multi-task learning and image translation.
To predict sound source locations in continuous space, effectively handling random source positions.

Main Methods:

Developed MTIT, a DNN framework with one encoder and two decoders for SSL.
The encoder extracts spatial features from beam-spectrum surfaces.
Two decoders address multipath resolution and source location prediction in parallel, leveraging shared representations.

More Related Videos

Localizing Function-specific Targets for Transcranial Magnetic Stimulation in the Absence of Navigation Equipment

Localizing Function-specific Targets for Transcranial Magnetic Stimulation in the Absence of Navigation Equipment

Published on: May 23, 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

Related Experiment Videos

Last Updated: Oct 11, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Localizing Function-specific Targets for Transcranial Magnetic Stimulation in the Absence of Navigation Equipment

Localizing Function-specific Targets for Transcranial Magnetic Stimulation in the Absence of Navigation Equipment

Published on: May 23, 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

Main Results:

MTIT demonstrated superior localization performance compared to baseline methods in simulated, measured, and real-world acoustic environments.
The method effectively resolved multipath effects caused by reverberation.
MTIT achieved strong generalization performance in dynamic environments.

Conclusions:

MTIT offers an effective deep learning approach for indoor sound source localization.
The multi-task learning strategy enhances the model's ability to handle complex acoustic conditions and generalize.
MTIT outperforms existing methods in dynamic environments, showing promise for real-world applications.