Keita Goto — accepted AI-conference papers

2026

ONLINE REGISTER FOR DUAL-MODE SELF-SUPERVISED SPEECH MODELS: MITIGATING THE LACK OF FUTURE CONTEXT

Keita Goto, Jinchuan Tian, Yusuke Shinohara, Shinji Watanabe

ICASSP 2026poster

Dual-mode self-supervised speech models (S3Ms), which jointly pre-trained in the offline and online mode, suffer from attention mismatch in streaming scenarios due to missing future context. To address this challenge, we proposed online registers, learnable tokens appended to each chunk in online mo…

Cited by 0 Source ↗PDF ↗Scholar ↗

2023

Step restriction for improving adversarial attacks

Keita Goto, Shinta Otake, Rei Kawakami, Nakamasa Inoue

ICASSP 2023accepted

We propose an algorithm to automatically restrict the step size in the iterative optimization process with an application to adversarial attacks on speaker verification models. The proposed algorithm dynamically determines a subspace with a restriction radius r to which the Taylor approximation is a…

Cited by 0 Source ↗Scholar ↗