SSPRL Lab GitHub Repository

• This page provides the research results of our project for developing the “Smartphone-Based Open Research Platform for Hearing Improvement Studies”. The research results provided here include the algorithms, codes(MATLAB, C/C++, Java, Objective-C files), research papers, user’s guides, technical documentations, and audio/video Demos developed in our Statistical Signal Processing Research Laboratory (SSPRL) in the Department of Electrical and Computer Engineering at the University of Texas at Dallas (UTD).

• The information and materials contained in this website is a presentation of the documented research work carried out by the faculty, students and personnel at UTD. This website including its content is available for public access with the understanding that UTD and the authorized faculty and students contributing to this website make no warranties, either expressed or implied, concerning the completeness, reliability, or suitability of the presented materials for any kind of applications. Neither UTD nor any contributor to this website and its content shall be held liable to any party for any use or misuse of the information and materials contained in this website in any form or shape. Nor does the UTD warrant that the use of this website information is free of any claims of copyright infringement. This website does not endorse any commercial providers or their products. UTD and faculty managing this website reserve the right to remove, update, alter, or take down any and all posted materials on this website at any time without notice.

Code Packages

Codes, User Guides can be downloaded from the GitHub repository listing below.

• DOA: Direction of Arrival Estimation and Speech source Localization
• SE: Speech Enhancement (including the speech classification and clinical testing)
• SI: Speaker Identification
• ASDS: Alert Signal Detection and Separation
• AFC: Acoustic Feedback Cancellation
• COMP: Compression, Fitting
• VAD: Voice Activation Detection
• FMIC: Framework for using Smartphone Microphones
• NC: Noise Classification
• GUI: Graphical User Interface

2021-2022

*Please contact Issa Panahi (issa.panahi@utdallas.edu) for the codes.

1. SE: Real-time joint dereverberation and speech enhancement for hearing aid applications using edge devices *
2. DOA: Joint Calibration and Synchronization of Two Arrays of Microphones and Loudspeakers Using Particle Swarm Optimization *
3. DOA: Robust Three-Microphone Speech Source Localization Using Randomized Singular Value Decomposition *
4. COMP: Development and Pilot Testing of Smartphone-Based Hearing Test Application *

2019-2020

*Please contact Issa Panahi (issa.panahi@utdallas.edu) for the codes.

1. ASDS: Alert signal detection and integration to speech enhancement*
2. SE: Speech Enhancement using super-Gaussian joint maximum a posteriori (SGJMAP) - SHARP 1
3. SE: Minimum Variance Distortionless Response (MVDR) + Speech Enhancement*
4. SE: A real-time convolutional neural network based speech enhancement for hearing impaired listeners using smartphone
5. SE: Efficient two-microphone speech enhancement using basic recurrent neural network cell for hearing and hearing aids *
6. SE: Real-time single-channel deep neural network-based speech enhancement on edge devices *
7. DOA: Real-Time Convolutional Neural Network Based Speech Source Localization on Smartphone
8. DOA: Direction of arrival estimation using deep neural network for hearing aid applications using smartphone
9. DOA: Convolutional Recurrent Neural Network Based Direction of Arrival Estimation Method Using Two Microphones for Hearing Studies *
10. DOA: Real-Time Estimation of Direction of Arrival of Speech Source using Three Microphones *
11. DOA: Spectral Flux-Based Convolutional Neural Network Architecture for Speech Source Localization and its Real-Time Implementation *
12. AFC: Adaptive Noise Injection Based Acoustic Feedback Cancellation*
13. COMP: Frequency based Adaptive Wide Dynamic Range Compression*
14. VAD: Automated machine learning: Speech classification for hearing aid applications and its real-time implementation on smartphone*