Domain-adaptation method between acoustic-response data using different insert earphones

Author:

Kim Kiyean1ORCID,Kim Sangyeon2,Sun Sukkyu3ORCID

Affiliation:

1. Mobile Experience Division, Samsung Electronics Co. Ltd 1 ., Suwon 443-742, Republic of Korea

2. Samsung Research, Samsung Electronics Co. Ltd 2 ., Seoul 06765, Republic of Korea

3. Department of AI Software Convergence, Dongguk University 3 , Seoul 04620, Republic of Korea

Abstract

Classifying acoustic responses captured through earphones offers valuable insights into nearby environments, such as whether the earphones are in or out of the ear. However, the performances of classification algorithms often suffer when applied to other devices due to domain mismatches. This study proposes a domain-adaptation method tailored for acoustic-response data from two distinct insert earphone models. The method trains a domain-adaptation function using a pair of datasets obtained from a set of acoustic loads, yielding a domain-adapted dataset suitable for training classification algorithms in a target domain. The effectiveness of this approach is validated through assessments of domain adaptation quality and resulting performance enhancements in the classification algorithm tasked with discerning whether an earphone is positioned inside or outside the ear. Importantly, our method requires significantly fewer measurements than the original dataset, reducing data collection time while providing a suitable training dataset for the target domain. Additionally, the method's reusability across future devices streamlines data collection time and efforts for the future devices.

Funder

Samsung

Publisher

Acoustical Society of America (ASA)

Reference38 articles.

1. Bilateral ear acoustic authentication: A biometric authentication system using both ears and a special earphone;Appl. Sci.,2022

2. EarEcho: Using ear canal echo for wearable authentication;Proc. ACM Interact. Mob. Wearable Ubiquitous Technol.,2019

3. Facial expression recognition using ear canal transfer function,2019

4. CanalScan: Tongue-jaw movement recognition via ear canal deformation sensing,2021

5. FaceListener: Recognizing human facial expressions via acoustic sensing on commodity headphones,2022

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3