17 citations · 57 across the 24 of their papers we have counts for
25 papers
YODAS v3: Over 1 Million Hours of High-Bandwidth, Stereophonic, Multilingual Speech
William Chen, Shinnosuke Takamichi, Sayaka Shiota +3
We present YODAS v3, a weakly-labeled speech corpus containing over 1.1 million hours of 48kHz multi-channel audio in 147 languages, released under a CC BY 3.0 license. YODAS v3 is…
Voice Privacy Preservation with Multiple Random Orthogonal Secret Keys: Attack Resistance Analysis
Kohei Tanaka, Hitoshi Kiya, Sayaka Shiota
Recently, opportunities to transmit speech data to deep learning models executed in the cloud have increased. This has led to growing concerns about speech privacy, including both…
Speech privacy-preserving methods using secret key for convolutional neural network models and their robustness evaluation
Shoko Niwa, Sayaka Shiota, Hitoshi Kiya
In this paper, we propose privacy-preserving methods with a secret key for convolutional neural network (CNN)-based models in speech processing tasks. In environments where untrust…
YODAS: Youtube-Oriented Dataset for Audio and Speech
Xinjian Li, Shinnosuke Takamichi, Takaaki Saeki +3
In this study, we introduce YODAS (YouTube-Oriented Dataset for Audio and Speech), a large-scale, multilingual dataset comprising currently over 500k hours of speech data in more t…
A Random Ensemble of Encrypted Vision Transformers for Adversarially Robust Defense
Ryota Iijima, Sayaka Shiota, Hitoshi Kiya
Deep neural networks (DNNs) are well known to be vulnerable to adversarial examples (AEs). In previous studies, the use of models encrypted with a secret key was demonstrated to be…
Efficient Fine-Tuning with Domain Adaptation for Privacy-Preserving Vision Transformer
Teru Nagamori, Sayaka Shiota, Hitoshi Kiya
We propose a novel method for privacy-preserving deep neural networks (DNNs) with the Vision Transformer (ViT). The method allows us not only to train models and test with visually…
A Random Ensemble of Encrypted models for Enhancing Robustness against Adversarial Examples
Ryota Iijima, Sayaka Shiota, Hitoshi Kiya
Deep neural networks (DNNs) are well known to be vulnerable to adversarial examples (AEs). In addition, AEs have adversarial transferability, which means AEs generated for a source…
A privacy-preserving method using secret key for convolutional neural network-based speech classification
Shoko Niwa, Sayaka Shiota, Hitoshi Kiya
In this paper, we propose a privacy-preserving method with a secret key for convolutional neural network (CNN)-based speech classification tasks. Recently, many methods related to…
Domain Adaptation for Efficiently Fine-tuning Vision Transformer with Encrypted Images
Teru Nagamori, Sayaka Shiota, Hitoshi Kiya
In recent years, deep neural networks (DNNs) trained with transformed data have been applied to various applications such as privacy-preserving learning, access control, and advers…
Enhanced Security with Encrypted Vision Transformer in Federated Learning
Rei Aso, Sayaka Shiota, Hitoshi Kiya
Federated learning is a learning method for training models over multiple participants without directly sharing their raw data, and it has been expected to be a privacy protection…
Enhanced Security against Adversarial Examples Using a Random Ensemble of Encrypted Vision Transformer Models
Ryota Iijima, Miki Tanaka, Sayaka Shiota +1
Deep neural networks (DNNs) are well known to be vulnerable to adversarial examples (AEs). In addition, AEs have adversarial transferability, which means AEs generated for a source…
Access Control of Semantic Segmentation Models Using Encrypted Feature Maps
Hiroki Ito, AprilPyone MaungMaung, Sayaka Shiota +1
In this paper, we propose an access control method with a secret key for semantic segmentation models for the first time so that unauthorized users without a secret key cannot bene…
Adversarial Detector with Robust Classifier
Takayuki Osakabe, Maungmaung Aprilpyone, Sayaka Shiota +1
Deep neural network (DNN) models are wellknown to easily misclassify prediction results by using input images with small perturbations, called adversarial examples. In this paper,…
An Overview of Compressible and Learnable Image Transformation with Secret Key and Its Applications
Hitoshi Kiya, AprilPyone MaungMaung, Yuma Kinoshita +2
This article presents an overview of image transformation with a secret key and its applications. Image transformation with a secret key enables us not only to protect visual infor…
JTubeSpeech: corpus of Japanese speech collected from YouTube for speech recognition and speaker verification
Shinnosuke Takamichi, Ludwig Kürzinger, Takaaki Saeki +2
In this paper, we construct a new Japanese speech corpus called "JTubeSpeech." Although recent end-to-end learning requires large-size speech corpora, open-sourced such corpora for…
A universal detector of CNN-generated images using properties of checkerboard artifacts in the frequency domain
Miki Tanaka, Sayaka Shiota, Hitoshi Kiya
We propose a novel universal detector for detecting images generated by using CNNs. In this paper, properties of checkerboard artifacts in CNN-generated images are considered, and…
A Privacy-Preserving Machine Learning Scheme Using EtC Images
Ayana Kawamura, Yuma Kinoshita, Takayuki Nakachi +2
We propose a privacy-preserving machine learning scheme with encryption-then-compression (EtC) images, where EtC images are images encrypted by using a block-based encryption metho…
An Image Fusion Scheme for Single-Shot High Dynamic Range Imaging with Spatially Varying Exposures
Chihiro Go, Yuma Kinoshita, Sayaka Shiota +1
This paper proposes a novel multi-exposure image fusion (MEF) scheme for single-shot high dynamic range imaging with spatially varying exposures (SVE). Single-shot imaging with SVE…
Single-Shot High Dynamic Range Imaging with Spatially Varying Exposures Considering Hue Distortion
Chihiro Go, Yuma Kinoshita, Sayaka Shiota +1
We proposes a novel single-shot high dynamic range imaging scheme with spatially varying exposures (SVE) considering hue distortion. Single-shot imaging with SVE enables us to capt…
A Retinex-based Image Enhancement Scheme with Noise Aware Shadow-up Function
Chien Cheng Chien, Yuma Kinoshita, Sayaka Shiota +1
This paper proposes a novel image contrast enhancement method based on both a noise aware shadow-up function and Retinex (retina and cortex) decomposition. Under low light conditio…
Privacy-Preserving SVM Computing by Using Random Unitary Transformation
Takahiro Maekawa, Takayuki Nakachi, Sayaka Shiota +1
A privacy-preserving Support Vector Machine (SVM) computing scheme is proposed in this paper. Cloud computing has been spreading in many fields. However, the cloud computing has so…
A Pseudo Multi-Exposure Fusion Method Using Single Image
Yuma Kinoshita, Sayaka Shiota, Hitoshi Kiya
This paper proposes a novel pseudo multi-exposure image fusion method based on a single image. Multi-exposure image fusion is used to produce images without saturation regions, by…
Multi-Exposure Image Fusion Based on Exposure Compensation
Yuma Kinoshita, Taichi Yoshida, Sayaka Shiota +1
This paper proposes a novel multi-exposure image fusion method based on exposure compensation. Multi-exposure image fusion is a method to produce images without color saturation re…
Super-Resolution using Convolutional Neural Networks without Any Checkerboard Artifacts
Yusuke Sugawara, Sayaka Shiota, Hitoshi Kiya
It is well-known that a number of excellent super-resolution (SR) methods using convolutional neural networks (CNNs) generate checkerboard artifacts. A condition to avoid the check…