Related papers: Encoder initialisation methods in the model augmen…

With the development of deep learning, neural network-based speech enhancement (SE) models have shown excellent performance. Meanwhile, it was shown that the development of self-supervised pre-trained models can be applied to various…

Automated requirement-to-code traceability link recovery, essential for industrial system quality and safety, is critically hindered by the scarcity of labeled data. To address this bottleneck, this paper proposes and validates a…

This study introduces a novel knowledge enhanced tokenisation mechanism, K-Tokeniser, for clinical text processing. Technically, at initialisation stage, K-Tokeniser populates global representations of tokens based on semantic types of…

The approximation and convergence properties of implicit neural representations (INRs) are known to be highly sensitive to parameter initialization strategies. While several data-driven initialization methods demonstrate significant…

Anomalies in time-series provide insights of critical scenarios across a range of industries, from banking and aerospace to information technology, security, and medicine. However, identifying anomalies in time-series data is particularly…

System identification uses measurements of a dynamic system's input and output to reconstruct a mathematical model for that system. These can be mechanical, electrical, physiological, among others. Since most of the systems around us…

Recently, the recurrent neural network transducer (RNN-T) architecture has become an emerging trend in end-to-end automatic speech recognition research due to its advantages of being capable for online streaming speech recognition. However,…

Deep learning-based models have greatly advanced the performance of speech enhancement (SE) systems. However, two problems remain unsolved, which are closely related to model generalizability to noisy conditions: (1) mismatched noisy…

Modeling time series data remains a pervasive issue as the temporal dimension is inherent to numerous domains. Despite significant strides in time series forecasting, high noise-to-signal ratio, non-normality, non-stationarity, and lack of…

Deep neural network-based systems have significantly improved the performance of speaker diarization tasks. However, end-to-end neural diarization (EEND) systems often struggle to generalize to scenarios with an unseen number of speakers,…

Mixed-signal artificial neural networks (ANNs) that employ analog matrix-multiplication accelerators can achieve higher speed and improved power efficiency. Though analog computing is known to be susceptible to noise and device…

The inherent heavy computation of deep neural networks prevents their widespread applications. A widely used method for accelerating model inference is quantization, by replacing the input operands of a network using fixed-point values.…

In recent research, in the domain of speech processing, large End-to-End (E2E) systems for Automatic Speech Recognition (ASR) have reported state-of-the-art performance on various benchmarks. These systems intrinsically learn how to handle…

Deep learning has been widely adopted to tackle various code-based tasks by building deep code models based on a large amount of code snippets. While these deep code models have achieved great success, even state-of-the-art models suffer…

The leading approach for image compression with artificial neural networks (ANNs) is to learn a nonlinear transform and a fixed entropy model that are optimized for rate-distortion performance. We show that this approach can be…

Supervised speech enhancement methods have been very successful. However, in practical scenarios, there is a lack of clean speech, and self-supervised learning-based (SSL) speech enhancement methods that offer comparable enhancement…

To adapt to real-world data streams, continual learning (CL) systems must rapidly learn new concepts while preserving and utilizing prior knowledge. When it comes to adding new information to continually-trained deep neural networks (DNNs),…

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…

This paper presents a novel identification approach of Koopman models of nonlinear systems with inputs under rather general noise conditions. The method uses deep state-space encoders based on the concept of state reconstructability and an…

Estimating the parameters of nonlinear block-oriented state-space models from input-output data typically involves solving a highly non-convex optimization problem, which is prone to poor local minima and slow convergence. This paper…