Ear acoustic authentication is a biometric authentication technology that recognizes the acoustic characteristics of the ear canal to authenticate users. However, compared to fingerprints, ear acoustic authentication has not been studied sufficiently with regards to the individuality of the acoustic characteristics of the ear canal. Therefore, a study on the visualization of ear canal acoustic characteristic differences using t-distributed stochastic neighbor embedding (t-SNE) which expresses the similarity in high-dimensional space and estimates the similarity in low-dimensional space, was conducted.

Authors: Ominato, Rei; Yano, Shohei; Wakui, Naoki; Wakui, Naoki; Takamichi, Shinnosuke
Affiliations: NIT, Nagaoka College; NIT, Nagaoka College; NIT, Nagaoka College; The University of Tokyo(See document for exact affiliation information.)
AES Convention: 148 (May 2020) Paper Number: 10350
Publication Date: May 28, 2020 Import into BibTeX
Subject: Applications
Permalink: https://www.aes.org/e-lib/browse.cfm?elib=20767

Click to purchase paper as a non-member or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member and would like to subscribe to the E-Library then Join the AES!

This paper costs $33 for non-members and is free for AES members and E-Library subscribers.

Learn more about the AES E-Library

E-Library Location:   /conv/148/10350.pdf

Start a discussion about this paper!