Related papers: Decoding Stimulus Reconstruction-Based Auditory At…
We address the fundamental incompatibility of attention-based encoder-decoder (AED) models with long-form acoustic encodings. AED models trained on segmented utterances learn to encode absolute frame positions by exploiting limited acoustic…
Unseen data conditions can inflict serious performance degradation on systems relying on supervised machine learning algorithms. Because data can often be unseen, and because traditional machine learning algorithms are trained in a…
Deep learning models tend to memorize training data, which hurts their ability to generalize to under-represented classes. We empirically study a convolutional neural network's internal representation of imbalanced image data and measure…
With the development of deep learning, medical image processing has been widely used to assist clinical research. This paper focuses on the denoising problem of low-dose computed tomography using deep learning. Although low-dose computed…
We introduce a novel data reconstruction algorithm known as Gappy auto-encoder (Gappy AE) to address the limitations associated with Gappy proper orthogonal decomposition (Gappy POD), a widely used method for data reconstruction when…
Predicting brain activity in response to naturalistic, multimodal stimuli is a key challenge in computational neuroscience. While encoding models are becoming more powerful, their ability to generalize to truly novel contexts remains a…
Central to active learning (AL) is what data should be selected for annotation. Existing works attempt to select highly uncertain or informative data for annotation. Nevertheless, it remains unclear how selected data impacts the test…
Sparse autoencoders (SAEs) are one of the main methods to interpret the inner workings of deep neural networks (DNNs), decomposing activations into higher-dimensional features. However, they exhibit critical shortcomings where a large…
Convolutional denoising autoencoders (DAEs) are powerful tools for image restoration. However, they inherit a key limitation of convolutional neural networks (CNNs): they tend to recover low-frequency features, such as smooth regions, more…
An autoencoder-based codec employs quantization to turn its bottleneck layer activation into bitstrings, a process that hinders information flow between the encoder and decoder parts. To circumvent this issue, we employ additional skip…
Anomalous sound detection (ASD) in the wild requires robustness to distribution shifts such as unseen low-SNR input mixtures of machine and noise types. State-of-the-art systems extract embeddings from an adapted audio encoder and detect…
EEG and audio are inherently distinct modalities, differing in sampling rate, channel structure, and scale. Yet, we show that pretrained neural audio codecs can serve as effective starting points for EEG compression, provided that the data…
Unified multimodal models for image generation and understanding represent a significant step toward AGI and have attracted widespread attention from researchers. The main challenge of this task lies in the difficulty in establishing an…
Training models on highly unbalanced data is admitted to be a challenging task for machine learning algorithms. Current studies on deep learning mainly focus on data sets with balanced class labels or unbalanced data, but with massive…
Unseen data can degrade performance of deep neural net acoustic models. To cope with unseen data, adaptation techniques are deployed. For unlabeled unseen data, one must generate some hypothesis given an existing model, which is used as the…
This technical report describes our system that is submitted to the Deep Noise Suppression Challenge and presents the results for the non-real-time track. To refine the estimation results stage by stage, we utilize recursive learning, a…
This paper introduces a novel algorithm designed for speech synthesis from neural activity recordings obtained using invasive electroencephalography (EEG) techniques. The proposed system offers a promising communication solution for…
Automated segmentation of structural defects from visual inspection imagery remains challenging due to the diversity of damage types, extreme class imbalance, and the need for precise boundary delineation. This paper presents DeltaSeg, a…
Silent speech decoding, which performs unvocalized human speech recognition from electroencephalography/electromyography (EEG/EMG), increases accessibility for speech-impaired humans. However, data collection is difficult and performed…
In this paper, we propose Normality-Calibrated Autoencoder (NCAE), which can boost anomaly detection performance on the contaminated datasets without any prior information or explicit abnormal samples in the training phase. The NCAE…