Related papers: Pre-training Autoencoder for Acoustic Event Classi…

High-speed vision sensing is essential for real-time perception in applications such as robotics, autonomous vehicles, and industrial automation. Traditional frame-based vision systems suffer from motion blur, high latency, and redundant…

Recent research has delved into speech enhancement (SE) approaches that leverage audio embeddings from pre-trained models, diverging from time-frequency masking or signal prediction techniques. This paper introduces an efficient and…

Acoustic Event Classification (AEC) has become a significant task for machines to perceive the surrounding auditory scene. However, extracting effective representations that capture the underlying characteristics of the acoustic events is…

Recently, a generative variational autoencoder (VAE) has been proposed for speech enhancement to model speech statistics. However, this approach only uses clean speech in the training phase, making the estimation particularly sensitive to…

Sound event detection (SED) is a task to detect sound events in an audio recording. One challenge of the SED task is that many datasets such as the Detection and Classification of Acoustic Scenes and Events (DCASE) datasets are weakly…

Automatic Audio Captioning (AAC) refers to the task of translating audio into a natural language that describes the audio events, source of the events and their relationships. The limited samples in AAC datasets at present, has set up a…

Low-light images suffer from severe noise and low illumination. Current deep learning models that are trained with real-world images have excellent noise reduction, but a ratio parameter must be chosen manually to complete the enhancement…

Diffusion autoencoders (DAEs) are typically formulated as a noise prediction model and trained with a linear-$\beta$ noise schedule that spends much of its sampling steps at high noise levels. Because high noise levels are associated with…

Artificial intelligence (AI) techniques, particularly autoencoders (AEs), have gained significant attention in wireless communication systems. This paper investigates using an AE to generate featureless signals with a low probability of…

Audio content analysis in terms of sound events is an important research problem for a variety of applications. Recently, the development of weak labeling approaches for audio or sound event detection (AED) and availability of large scale…

This paper presents a new preprocessing method to correct blinking artifacts in Electroencephalography (EEG) based Brain-Computer Interfaces (BCIs). This Algorithm for Blink Correction (ABC) directly corrects the signal in the time domain…

Current EEG/MEG-to-text decoding systems suffer from three key limitations: (1) reliance on teacher-forcing methods, which compromises robustness during inference, (2) sensitivity to session-specific noise, hindering generalization across…

Transformers have revolutionized the world of deep learning, specially in the field of natural language processing. Recently, the Audio Spectrogram Transformer (AST) was proposed for audio classification, leading to state of the art results…

Accent classification or AC is a task to predict the accent type of an input utterance, and it can be used as a preliminary step toward accented speech recognition and accent conversion. Existing studies have often achieved such…

We argue that training autoencoders to reconstruct inputs from noised versions of their encodings, when combined with perceptual losses, yields encodings that are structured according to a perceptual hierarchy. We demonstrate the emergence…

Recently, a variety of acoustic tasks and related applications arised. For many acoustic tasks, the labeled data size may be limited. To handle this problem, we propose an unsupervised pre-training method using Transformer based encoder to…

We show that compact fully connected (FC) deep learning networks trained to classify wireless protocols using a hierarchy of multiple denoising autoencoders (AEs) outperform reference FC networks trained in a typical way, i.e., with a…

Acoustic scene classification (ASC) predominantly relies on supervised approaches. However, acquiring labeled data for training ASC models is often costly and time-consuming. Recently, self-supervised learning (SSL) has emerged as a…

In surveillance, monitoring and tactical reconnaissance, gathering the right visual information from a dynamic environment and accurately processing such data are essential ingredients to making informed decisions which determines the…

In industry, machine anomalous sound detection (ASD) is in great demand. However, collecting enough abnormal samples is difficult due to the high cost, which boosts the rapid development of unsupervised ASD algorithms. Autoencoder (AE)…