相关论文: Quaternion Neural Networks for Multi-channel Dista…

Automatic speech recognition (ASR) has recently become an important challenge when using deep learning (DL). It requires large-scale training datasets and high computational and storage resources. Moreover, DL techniques and machine…

Multilingual training has been shown to improve acoustic modeling performance by sharing and transferring knowledge in modeling different languages. Knowledge sharing is usually achieved by using common lower-level layers for different…

While the transformer has emerged as the eminent neural architecture, several independent lines of research have emerged to address its limitations. Recurrent neural approaches have observed a lot of renewed interest, including the extended…

Learning from data in the quaternion domain enables us to exploit internal dependencies of 4D signals and treating them as a single entity. One of the models that perfectly suits with quaternion-valued data processing is represented by 3D…

Few-shot segmentation (FSS) aims to segment unseen classes given only a few annotated samples. Encouraging progress has been made for FSS by leveraging semantic features learned from base classes with sufficient training samples to…

Vanishing long-term gradients are a major issue in training standard recurrent neural networks (RNNs), which can be alleviated by long short-term memory (LSTM) models with memory cells. However, the extra parameters associated with the…

In real-world applications, automatic speech recognition (ASR) systems must handle overlapping speech from multiple speakers and recognize rare words like technical terms. Traditional methods address multi-talker ASR and contextual biasing…

The performance of automatic speech recognition (ASR) systems severely degrades when multi-talker speech overlap occurs. In meeting environments, speech separation is typically performed to improve the robustness of ASR systems. Recently,…

We have recently shown that deep Long Short-Term Memory (LSTM) recurrent neural networks (RNNs) outperform feed forward deep neural networks (DNNs) as acoustic models for speech recognition. More recently, we have shown that the performance…

Recurrent neural networks (RNNs), including long short-term memory (LSTM) RNNs, have produced state-of-the-art results on a variety of speech recognition tasks. However, these models are often too large in size for deployment on mobile…

Distant speech recognition is a challenge, particularly due to the corruption of speech signals by reverberation caused by large distances between the speaker and microphone. In order to cope with a wide range of reverberations in…

Speaker-independent speech separation has achieved remarkable performance in recent years with the development of deep neural network (DNN). Various network architectures, from traditional convolutional neural network (CNN) and recurrent…

Quaternion neural networks are parameter-efficient and model multidimensional dependencies by representing four related features as a single entity. However, existing quaternion self-attention computes component-wise scores and applies…

Deep learning has achieved substantial improvement on single-channel speech enhancement tasks. However, the performance of multi-layer perceptions (MLPs)-based methods is limited by the ability to capture the long-term effective history…

State-of-the-art neural network language models (NNLMs) represented by long short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming highly complex. They are prone to overfitting and poor generalization when…

Deep neural networks have achieved great success in computer vision, speech recognition and many other areas. The potential of recurrent neural networks especially the Long Short-Term Memory (LSTM) for open set communication signal…

The problem of effectively exploiting the information multiple data sources has become a relevant but challenging research topic in remote sensing. In this paper, we propose a new approach to exploit the complementarity of two data sources:…

We study the problem of compressing recurrent neural networks (RNNs). In particular, we focus on the compression of RNN acoustic models, which are motivated by the goal of building compact and accurate speech recognition systems which can…

In recent years, deep learning has presented a great advance in hyperspectral image (HSI) classification. Particularly, long short-term memory (LSTM), as a special deep learning structure, has shown great ability in modeling long-term…

The echo state network (ESN) is a powerful and efficient tool for displaying dynamic data. However, many existing ESNs have limitations for properly modeling high-dimensional data. The most important limitation of these networks is the high…