Related papers: StutterNet: Stuttering Detection Using Time Delay …
Epilepsy is common neurological diseases, affecting about 0.6-0.8 % of world population. Epileptic patients suffer from chronic unprovoked seizures, which can result in broad spectrum of debilitating medical and social consequences. Since…
This paper presents an improved deep embedding learning method based on convolutional neural network (CNN) for text-independent speaker verification. Two improvements are proposed for x-vector embedding learning: (1) Multi-scale convolution…
With the fast development of deep learning, it has become common to learn big neural networks using massive training data. Asynchronous Stochastic Gradient Descent (ASGD) is widely adopted to fulfill this task for its efficiency, which is,…
This thesis presents and evaluates the Dilated Convolution with Learnable Spacings (DCLS) method. Through various supervised learning experiments in the fields of computer vision, audio, and speech processing, the DCLS method proves to…
Spiking neural networks have gained significant attention due to their brain-like information processing capabilities. The use of surrogate gradients has made it possible to train spiking neural networks with backpropagation, leading to…
The recent advances in deep learning are mostly driven by availability of large amount of training data. However, availability of such data is not always possible for specific tasks such as speaker recognition where collection of large…
Sparse deep learning has become a popular technique for improving the performance of deep neural networks in areas such as uncertainty quantification, variable selection, and large-scale network compression. However, most existing research…
Reliable detection of the prodromal stages of Alzheimer's disease (AD) remains difficult even today because, unlike other neurocognitive impairments, there is no definitive diagnosis of AD in vivo. In this context, existing research has…
This paper describes a novel deep learning-based method for mitigating the effects of atmospheric distortion. We have built an end-to-end supervised convolutional neural network (CNN) to reconstruct turbulence-corrupted video sequence. Our…
The demand for low-power inference and training of deep neural networks (DNNs) on edge devices has intensified the need for algorithms that are both scalable and energy-efficient. While spiking neural networks (SNNs) allow for efficient…
End-to-end model, especially Recurrent Neural Network Transducer (RNN-T), has achieved great success in speech recognition. However, transducer requires a great memory footprint and computing time when processing a long decoding sequence.…
In this paper, we present a time-contrastive learning (TCL) based bottleneck (BN)feature extraction method for speech signals with an application to text-dependent (TD) speaker verification (SV). It is well-known that speech signals exhibit…
Deep spiking neural networks (SNNs) hold great potential for improving the latency and energy efficiency of deep neural networks through event-based computation. However, training such networks is difficult due to the non-differentiable…
Detecting anomalies from a series of temporal networks has many applications, including road accidents in transport networks and suspicious events in social networks. While there are many methods for network anomaly detection, statistical…
Time-frequency analysis is an important and challenging task in many applications. Fourier and wavelet analysis are two classic methods that have achieved remarkable success in many fields. However, they also exhibit limitations when…
Dysfluent speech modeling requires time-accurate and silence-aware transcription at both the word-level and phonetic-level. However, current research in dysfluency modeling primarily focuses on either transcription or detection, and the…
Considering the models that apply the contextual information of time-series data could improve the fault diagnosis performance, some neural network structures such as RNN, LSTM, and GRU were proposed to model the fault diagnosis…
We propose a DTCWT ScatterNet Convolutional Neural Network (DTSCNN) formed by replacing the first few layers of a CNN network with a parametric log based DTCWT ScatterNet. The ScatterNet extracts edge based invariant representations that…
Clipping is a common nonlinear distortion that occurs whenever the input or output of an audio system exceeds the supported range. This phenomenon undermines not only the perception of speech quality but also downstream processes utilizing…
Many real-world time-series analysis problems are characterised by scarce data. Solutions typically rely on hand-crafted features extracted from the time or frequency domain allied with classification or regression engines which condition…