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

Audio autoencoders learn useful, compressed audio representations, but their non-linear latent spaces prevent intuitive algebraic manipulation such as mixing or scaling. We introduce a simple training methodology to induce linearity in a…

Decoding the attended speaker in a multi-speaker environment from electroencephalography (EEG) has attracted growing interest in recent years, with neuro-steered hearing devices as a driver application. Current approaches typically rely on…

Self-supervised learning has been a powerful training paradigm to facilitate representation learning. In this study, we design a masked autoencoder (MAE) to guide deep learning models to learn electroencephalography (EEG) signal…

Unsupervised disentangled representation learning from the unlabelled audio data, and high fidelity audio generation have become two linchpins in the machine learning research fields. However, the representation learned from an unsupervised…

Audio self-supervised learning (SSL) pre-training, which aims to learn good representations from unlabeled audio, has made remarkable progress. However, the extensive computational demands during pre-training pose a significant barrier to…

In this paper, we present a deep learning framework applied for Acoustic Scene Classification (ASC), the task of classifying scene contexts from environmental input sounds. An ASC system generally comprises of two main steps, referred to as…

Data encoding is a common and central operation in most data analysis tasks. The performance of other models downstream in the computational process highly depends on the quality of data encoding. One of the most powerful ways to encode…

Children speech recognition is indispensable but challenging due to the diversity of children's speech. In this paper, we propose a filter-based discriminative autoencoder for acoustic modeling. To filter out the influence of various…

Extracellular recordings are severely contaminated by a considerable amount of noise sources, rendering the denoising process an extremely challenging task that should be tackled for efficient spike sorting. To this end, we propose an…

Strong gravitational lensing can reveal the influence of dark-matter substructure in galaxies, but analyzing these effects from noisy, low-resolution images poses a significant challenge. In this work, we propose a masked autoencoder (MAE)…

Speech 'in-the-wild' is a handicap for speaker recognition systems due to the variability induced by real-life conditions, such as environmental noise and the emotional state of the speaker. Taking advantage of the principles of…

Recently, deep learning becomes the main focus of machine learning research and has greatly impacted many important fields. However, deep learning is criticized for lack of interpretability. As a successful unsupervised model in deep…

Evaluating canine electrocardiograms (ECGs) is challenging due to noise that can obscure clinically relevant cardiac electrical activity. Common sources of interference include respiration, muscle activity, poor lead contact, and external…

Unsupervised anomalous sound detection (ASD) aims to detect unknown anomalous sounds of devices when only normal sound data is available. The autoencoder (AE) and self-supervised learning based methods are two mainstream methods. However,…

Speech emotion recognition (SER) systems often struggle in real-world environments, where ambient noise severely degrades their performance. This paper explores a novel approach that exploits prior knowledge of testing environments to…

Sparse Autoencoders (SAEs) are powerful tools for interpreting neural representations, yet their use in audio remains underexplored. We train SAEs across all encoder layers of Whisper and HuBERT, provide an extensive evaluation of their…

Denoising autoencoders (DAEs) are powerful deep learning models used for feature extraction, data generation and network pre-training. DAEs consist of an encoder and decoder which may be trained simultaneously to minimise a loss (function)…

The advances in attention-based encoder-decoder (AED) networks have brought great progress to end-to-end (E2E) automatic speech recognition (ASR). One way to further improve the performance of AED-based E2E ASR is to introduce an extra text…

Audio captioning is an important research area that aims to generate meaningful descriptions for audio clips. Most of the existing research extracts acoustic features of audio clips as input to encoder-decoder and transformer architectures…

The design of new methods and models when only weakly-labeled data are available is of paramount importance in order to reduce the costs of manual annotation and the considerable human effort associated with it. In this work, we address…