Related papers: Arc-swift: A Novel Transition System for Dependenc…

In recent years, vision transformers with text decoder have demonstrated remarkable performance on Scene Text Recognition (STR) due to their ability to capture long-range dependencies and contextual relationships with high learning…

This paper proposes a novel label-synchronous speech-to-text alignment technique for automatic speech recognition (ASR). The speech-to-text alignment is a problem of splitting long audio recordings with un-aligned transcripts into…

This paper describes a new statistical parser which is based on probabilities of dependencies between head-words in the parse tree. Standard bigram probability estimation techniques are extended to calculate probabilities of dependencies…

Transformer-based architectures are the most used architectures in many deep learning fields like Natural Language Processing, Computer Vision or Speech processing. It may encourage the direct use of Transformers in the constrained tasks,…

Neural transducers provide a natural way of streaming ASR. However, they augment output sequences with blank tokens which leads to challenges for domain adaptation using text data. This paper proposes a label-synchronous neural transducer…

Test-time adaptation is a promising research direction that allows the source model to adapt itself to changes in data distribution without any supervision. Yet, current methods are usually evaluated on benchmarks that are only a…

In the cascaded approach to spoken language translation (SLT), the ASR output is typically punctuated and segmented into sentences before being passed to MT, since the latter is typically trained on written text. However, erroneous…

Reachability analysis, in general, is a fundamental method that supports formally-correct synthesis, robust model predictive control, set-based observers, fault detection, invariant computation, and conformance checking, to name but a few.…

Transformer is a powerful model for text understanding. However, it is inefficient due to its quadratic complexity to input sequence length. Although there are many methods on Transformer acceleration, they are still either inefficient on…

Transformer-based approaches have demonstrated remarkable success in various sequence-based tasks. However, traditional self-attention models may not sufficiently capture the intricate dependencies within items in sequential recommendation…

Dynamic graph learning plays a pivotal role in modeling evolving relationships over time, especially for temporal link prediction tasks in domains such as traffic systems, social networks, and recommendation platforms. While…

Current ASR systems are mainly trained and evaluated at the utterance level. Long range cross utterance context can be incorporated. A key task is to derive a suitable compact representation of the most relevant history contexts. In…

Given new tasks with very little data$-$such as new classes in a classification problem or a domain shift in the input$-$performance of modern vision systems degrades remarkably quickly. In this work, we illustrate how the neural network…

Recent advancements in attention mechanisms have replaced recurrent neural networks and its variants for machine translation tasks. Transformer using attention mechanism solely achieved state-of-the-art results in sequence modeling. Neural…

The introduction of pre-trained transformer-based contextualized word embeddings has led to considerable improvements in the accuracy of graph-based parsers for frameworks such as Universal Dependencies (UD). However, previous works differ…

Transformer-based end-to-end (E2E) automatic speech recognition (ASR) systems have recently gained wide popularity, and are shown to outperform E2E models based on recurrent structures on a number of ASR tasks. However, like other E2E…

Compressed sensing can decrease scanning transmission electron microscopy electron dose and scan time with minimal information loss. Traditionally, sparse scans used in compressed sensing sample a static set of probing locations. However,…

Contextual biasing is essential to improving the recognition of rare and domain-specific words in an automatic speech recognition (ASR) system. While numerous methods have been proposed in recent years, most of them focus on offline…

Modelling long-range dependencies is critical for scene understanding tasks in computer vision. Although convolution neural networks (CNNs) have excelled in many vision tasks, they are still limited in capturing long-range structured…

The dominant paradigm for semantic parsing in recent years is to formulate parsing as a sequence-to-sequence task, generating predictions with auto-regressive sequence decoders. In this work, we explore an alternative paradigm. We formulate…