Related papers: Powerful and Extensible WFST Framework for RNN-Tra…

The recurrent neural network transducer (RNN-T) is a prominent streaming end-to-end (E2E) ASR technology. In RNN-T, the acoustic encoder commonly consists of stacks of LSTMs. Very recently, as an alternative to LSTM layers, the Conformer…

Pretrained Foundation Models (PFMs) have transformed numerous applications by enabling efficient adaptation to customized tasks. Parameter-Efficient Fine-Tuning (PEFT) has emerged as a resource-efficient alternative to full fine-tuning,…

Extremely efficient convolutional neural network architectures are one of the most important requirements for limited-resource devices (such as embedded and mobile devices). The computing power and memory size are two important constraints…

Sparse neural networks are important for achieving better generalization and enhancing computation efficiency. This paper proposes a novel learning approach to obtain sparse fully connected layers in neural networks (NNs) automatically. We…

Recently, recurrent neural network transducer (RNN-T) gains increasing popularity due to its natural streaming capability as well as superior performance. Nevertheless, RNN-T training requires large time and computation resources as RNN-T…

In this paper, we design a new class of high-efficiency deep joint source-channel coding methods to achieve end-to-end video transmission over wireless channels. The proposed methods exploit nonlinear transform and conditional coding…

Tensor completion aimes at recovering missing data, and it is one of the popular concerns in deep learning and signal processing. Among the higher-order tensor decomposition algorithms, the recently proposed fully-connected tensor network…

Transformers are set to become ubiquitous with applications ranging from chatbots and educational assistants to visual recognition and remote sensing. However, their increasing computational and memory demands is resulting in growing energy…

The increasing demand for on-device training of deep neural networks (DNNs) aims to leverage personal data for high-performance applications while addressing privacy concerns and reducing communication latency. However, resource-constrained…

This study presents a novel fault diagnosis model for urban rail transit systems based on Wavelet Transform Residual Neural Network (WT-ResNet). The model integrates the advantages of wavelet transform for feature extraction and ResNet for…

Modern deep neural networks (DNNs) are extremely powerful; however, this comes at the price of increased depth and having more parameters per layer, making their training and inference more computationally challenging. In an attempt to…

When learning graph neural networks (GNNs) in node-level prediction tasks, most existing loss functions are applied for each node independently, even if node embeddings and their labels are non-i.i.d. because of their graph structures. To…

We propose a finite-state transducer (FST) representation for the models used to decode keyboard inputs on mobile devices. Drawing from learnings from the field of speech recognition, we describe a decoding framework that can satisfy the…

Past years have witnessed rapid developments in Neural Machine Translation (NMT). Most recently, with advanced modeling and training techniques, the RNN-based NMT (RNMT) has shown its potential strength, even compared with the well-known…

We introduce a novel framework for Generalized Tensor Transforms (GTTs), constructed through an $n$-fold tensor product of an arbitrary $b \times b$ unitary matrix $W$. This construction generalizes many established transforms, by providing…

While the Kaldi framework provides state-of-the-art components for speech recognition like feature extraction, deep neural network (DNN)-based acoustic models, and a weighted finite state transducer (WFST)-based decoder, it is difficult to…

Recurrent Neural Networks (RNNs) are among the most successful machine learning models for sequence modelling, but tend to suffer from an exponential increase in the number of parameters when dealing with large multidimensional data. To…

Beam search, which is the dominant ASR decoding algorithm for end-to-end models, generates tree-structured hypotheses. However, recent studies have shown that decoding with hypothesis merging can achieve a more efficient search with…

We address the problem of reconstructing sparse signals from noisy and compressive measurements using a feed-forward deep neural network (DNN) with an architecture motivated by the iterative shrinkage-thresholding algorithm (ISTA). We…

Knowledge Distillation is an effective method of transferring knowledge from a large model to a smaller model. Distillation can be viewed as a type of model compression, and has played an important role for on-device ASR applications. In…