Personalization of Hearing Aid Compression by Human-in-the-Loop Deep Reinforcement Learning

被引：12

作者：

Alamdari, Nasim ^{[1
]}

Lobarinas, Edward ^{[2
]}

Kehtarnavaz, Nasser ^{[1
]}

机构：

[1] Univ Texas Dallas, Elect & Comp Engn Dept, Richardson, TX 75080 USA

[2] Univ Texas Dallas, Callier Ctr Commun Disorders, Richardson, TX 75080 USA

来源：

IEEE ACCESS | 2020年 / 8卷

关键词：

Personalized audio compression; deep reinforcement learning; human-in-the-loop personalization; personalized hearing aid; hearing aid compression;

D O I：

10.1109/ACCESS.2020.3035728

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Existing prescriptive compression strategies used in hearing aid fitting are designed based on gain averages from a group of users which may not be necessarily optimal for a specific user. Nearly half of hearing aid users prefer settings that differ from the commonly prescribed settings. This paper presents a human-in-the-loop deep reinforcement learning approach that personalizes hearing aid compression to achieve improved hearing perception. The developed approach is designed to learn a specific user's hearing preferences in order to optimize compression based on the user's feedbacks. Both simulation and subject testing results are reported. These results demonstrate the proof-of-concept of achieving personalized compression via human-in-the-loop deep reinforcement learning.

引用

页码：203503 / 203515

页数：13

共 50 条

[1] Human-in-the-loop Reinforcement Learning
Liang, Huanghuang
Yang, Lu
Cheng, Hong
Tu, Wenzhe
Xu, Mengjie
[J]. 2017 CHINESE AUTOMATION CONGRESS (CAC), 2017, : 4511 - 4518
[2] Thermal comfort management leveraging deep reinforcement learning and human-in-the-loop
Cicirelli, Franco
Guerrieri, Antonio
Mastroianni, Carlo
Spezzano, Giandomenico
Vinci, Andrea
[J]. PROCEEDINGS OF THE 2020 IEEE INTERNATIONAL CONFERENCE ON HUMAN-MACHINE SYSTEMS (ICHMS), 2020, : 160 - 165
[3] Deep Reinforcement Active Learning for Human-In-The-Loop Person Re-Identification
Liu, Zimo
Wang, Jingya
Gong, Shaogang
Lu, Huchuan
Tao, Dacheng
[J]. 2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, : 6121 - 6130
[4] Value Driven Representation for Human-in-the-Loop Reinforcement Learning
Keramati, Ramtin
Brunskill, Emma
[J]. ACM UMAP '19: PROCEEDINGS OF THE 27TH ACM CONFERENCE ON USER MODELING, ADAPTATION AND PERSONALIZATION, 2019, : 176 - 180
[5] Reinforcement Learning Requires Human-in-the-Loop Framing and Approaches
Taylor, Matthew E.
[J]. HHAI 2023: AUGMENTING HUMAN INTELLECT, 2023, 368 : 351 - 360
[6] Where to Add Actions in Human-in-the-Loop Reinforcement Learning
Mandel, Travis
Liu, Yun-En
Brunskill, Emma
Popovic, Zoran
[J]. THIRTY-FIRST AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2017, : 2322 - 2328
[7] End-to-end grasping policies for human-in-the-loop robots via deep reinforcement learning
Sharif, Mohammadreza
Erdogmus, Deniz
Amato, Christopher
Padir, Taskin
[J]. 2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021), 2021, : 2768 - 2774
[8] HEIDL: Learning Linguistic Expressions with Deep Learning and Human-in-the-Loop
Yang, Yiwei
Kandogan, Eser
Li, Yunyao
Lasecki, Walter S.
Sen, Prithviraj
[J]. PROCEEDINGS OF THE 57TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: SYSTEM DEMONSTRATIONS, (ACL 2019), 2019, : 135 - 140
[9] ASHA: Assistive Teleoperation via Human-in-the-Loop Reinforcement Learning
Chen, Sean
Gao, Jensen
Reddy, Siddharth
Berseth, Glen
Dragan, Anca D.
Levine, Sergey
[J]. 2022 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, ICRA 2022, 2022, : 7505 - 7512
[10] Optimal Volt/Var Control for Unbalanced Distribution Networks With Human-in-the-Loop Deep Reinforcement Learning
Sun, Xianzhuo
Xu, Zhao
Qiu, Jing
Liu, Huichuan
Wu, Huayi
Tao, Yuechuan
[J]. IEEE TRANSACTIONS ON SMART GRID, 2024, 15 (03) : 2639 - 2651

← 1 2 3 4 5 →