Related papers: E-PANNs: Sound Recognition Using Efficient Pre-tra…

State-of-the-art speech recognition systems typically employ neural network acoustic models. However, compared to Gaussian mixture models, deep neural network (DNN) based acoustic models often have many more model parameters, making it…

Mental fatigue increases the risk of operator error in language comprehension tasks. In order to prevent operator performance degradation, we used EEG signals to assess the mental fatigue of operators in human-computer systems. This study…

Semantically-aligned $(speech, image)$ datasets can be used to explore "visually-grounded speech". In a majority of existing investigations, features of an image signal are extracted using neural networks "pre-trained" on other tasks (e.g.,…

In this paper, we present an end-to-end approach for environmental sound classification based on a 1D Convolution Neural Network (CNN) that learns a representation directly from the audio signal. Several convolutional layers are used to…

Background: Active noise cancellation has been a subject of research for decades. Traditional techniques, like the Fast Fourier Transform, have limitations in certain scenarios. This research explores the use of deep neural networks (DNNs)…

Audio tagging aims to label sound events appearing in an audio recording. In this paper, we propose region-specific audio tagging, a new task which labels sound events in a given region for spatial audio recorded by a microphone array. The…

Recent advancements in foundation models have sparked interest in respiratory audio foundation models. However, the effectiveness of applying conventional pre-training schemes to datasets that are small-sized and lack diversity has not been…

In this paper, we propose a method for incremental learning of two distinct tasks over time: acoustic scene classification (ASC) and audio tagging (AT). We use a simple convolutional neural network (CNN) model as an incremental learner to…

Electroencephalography (EEG)-based auditory attention detection (AAD) offers a non-invasive way to enhance hearing aids, but conventional methods rely on too many electrodes, limiting wearability and comfort. This paper presents SHAP-AAD, a…

Deep neural networks can learn complex and abstract representations, that are progressively obtained by combining simpler ones. A recent trend in speech and speaker recognition consists in discovering these representations starting from raw…

Previous acoustic transfer methods rely on extensive precomputation and storage of data to enable real-time interaction and auditory feedback. However, these methods struggle with complex scenes, especially when dynamic changes in object…

In addition to being extremely non-linear, modern problems require millions if not billions of parameters to solve or at least to get a good approximation of the solution, and neural networks are known to assimilate that complexity by…

This paper presents a hardware-efficient deep neural network (DNN), optimized through hardware-aware neural architecture search (HW-NAS); the DNN supports the classification of session-level encrypted traffic on resource-constrained…

Scene recognition is important for hearing devices, however; this is challenging, in part because of the limitations of existing datasets. Datasets often lack public accessibility, completeness, or audiologically relevant labels, hindering…

In this paper, we present EH-MAM (Easy-to-Hard adaptive Masked Acoustic Modeling), a novel self-supervised learning approach for speech representation learning. In contrast to the prior methods that use random masking schemes for Masked…

Transformers have set new benchmarks in audio processing tasks, leveraging self-attention mechanisms to capture complex patterns and dependencies within audio data. However, their focus on pairwise interactions limits their ability to…

Transfer learning is a crucial concept within deep learning that allows artificial neural networks to benefit from a large pre-training data basis when confronted with a task of limited data. Despite its ubiquitous use and clear benefits,…

Convolutional neural networks (CNN) are one of the best-performing neural network architectures for environmental sound classification (ESC). Recently, temporal attention mechanisms have been used in CNN to capture the useful information…

Neural networks with Auto-regressive structures, such as Recurrent Neural Networks (RNNs), have become the most appealing structures for acoustic modeling of parametric text to speech synthesis (TTS) in ecent studies. Despite the prominent…

State-of-the-art pre-trained language models have been shown to memorise facts and perform well with limited amounts of training data. To gain a better understanding of how these models learn, we study their generalisation and memorisation…