Zobrazeno 1 - 10
of 130
pro vyhledávání: '"KASHINO, Kunio"'
To reduce the need for skilled clinicians in heart sound interpretation, recent studies on automating cardiac auscultation have explored deep learning approaches. However, despite the demands for large data for deep learning, the size of the heart so
Externí odkaz:
http://arxiv.org/abs/2404.17107
Self-supervised learning (SSL) using masked prediction has made great strides in general-purpose audio representation. This study proposes Masked Modeling Duo (M2D), an improved masked prediction SSL, which learns by predicting representations of mas
Externí odkaz:
http://arxiv.org/abs/2404.06095
Autor:
Matsuo, Shinnosuke, Wu, Xiaomeng, Atarsaikhan, Gantugs, Kimura, Akisato, Kashino, Kunio, Iwana, Brian Kenji, Uchida, Seiichi
Similarity measures for time series are important problems for time series classification. To handle the nonlinear time distortions, Dynamic Time Warping (DTW) has been widely used. However, DTW is not learnable and suffers from a trade-off between r
Externí odkaz:
http://arxiv.org/abs/2309.06720
We proposed Audio Difference Captioning (ADC) as a new extension task of audio captioning for describing the semantic differences between input pairs of similar but slightly different audio clips. The ADC solves the problem that conventional audio ca
Externí odkaz:
http://arxiv.org/abs/2308.11923
Self-supervised learning general-purpose audio representations have demonstrated high performance in a variety of tasks. Although they can be optimized for application by fine-tuning, even higher performance can be expected if they can be specialized
Externí odkaz:
http://arxiv.org/abs/2305.14079
Masked Autoencoders is a simple yet powerful self-supervised learning method. However, it learns representations indirectly by reconstructing masked input patches. Several methods learn representations directly by predicting representations of masked
Externí odkaz:
http://arxiv.org/abs/2210.14648
Despite recent advances in image enhancement, it remains difficult for existing approaches to adaptively improve the brightness and contrast for both low-light and normal-light images. To solve this problem, we propose a novel 2D histogram equalizati
Externí odkaz:
http://arxiv.org/abs/2209.06406
Existing image enhancement methods fall short of expectations because with them it is difficult to improve global and local image contrast simultaneously. To address this problem, we propose a histogram equalization-based method that adapts to the da
Externí odkaz:
http://arxiv.org/abs/2209.06405
Autor:
Ohishi, Yasunori, Delcroix, Marc, Ochiai, Tsubasa, Araki, Shoko, Takeuchi, Daiki, Niizumi, Daisuke, Kimura, Akisato, Harada, Noboru, Kashino, Kunio
We propose a novel framework for target speech extraction based on semantic information, called ConceptBeam. Target speech extraction means extracting the speech of a target speaker in a mixture. Typical approaches have been exploiting properties of
Externí odkaz:
http://arxiv.org/abs/2207.11964
The amount of audio data available on public websites is growing rapidly, and an efficient mechanism for accessing the desired data is necessary. We propose a content-based audio retrieval method that can retrieve a target audio that is similar to bu
Externí odkaz:
http://arxiv.org/abs/2207.09732