An Individualized Super-Gaussian Single Microphone Speech Enhancement for Hearing Aid Users With Smartphone as an Assistive Device
This GitHub repository provides for single channel SE on iOS smartphone platforms. The example app provided here is for hearing improvement studies.
Abstract: In this letter, we derive a new super-Gaussian joint maximum a posteriori (SGJMAP) based single microphone speech enhancement gain function. The developed speech enhancement method is implemented on a smartphone, and this arrangement functions as an assistive device to hearing aids. We introduce a tradeoff parameter in the derived gain function that allows the smartphone user to customize their listening preference, by controlling the amount of noise suppression and speech distortion in real-time based on their level of hearing comfort perceived in noisy real-world acoustic environment. Objective quality and intelligibility measures show the effectiveness of the proposed method in comparison to benchmark techniques considered in this letter. Subjective results reflect the usefulness of the developed speech enhancement application in real-world noisy conditions at signal to noise ratio levels of -5, 0, and 5 dB.
You can find the paper for this GitHub repository : https://ieeexplore.ieee.org/document/8031044
https://www.youtube.com/watch?v=tRu9vGS_EtM&feature=emb_logo
- iPhone 7 running iOS 10.3
The codes are licensed under open-source MIT license.
For any utilization of the code content of this repository, one of the following books needs to get cited by the user:
- C. Karadagur Ananda Reddy, N. Shankar, G. Shreedhar Bhat, R. Charan and I. Panahi, "An Individualized Super-Gaussian Single Microphone Speech Enhancement for Hearing Aid Users With Smartphone as an Assistive Device," in IEEE Signal Processing Letters, vol. 24, no. 11, pp. 1601-1605, Nov. 2017, doi: 10.1109/LSP.2017.2750979.
- This work was supported in part by the National Institute of the Deafness and Other Communication Disorders (NIDCD) of the National Institutes of Health (NIH) under Award 1R01DC015430-02. The content is solely the responsibility of the authors and does not necessarily represent the official views of the NIH.
- 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 the University of Texas at Dallas (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.