相关论文: The Statistical Model for Ticker, an Adaptive Sing…

International Classification of Disease (ICD) coding procedure which refers to tagging medical notes with diagnosis codes has been shown to be effective and crucial to the billing system in medical sector. Currently, ICD codes are assigned…

This paper introduces real time inverse arithmetic coding and user interfaces based thereupon. The main idea is that information-efficient data entry can be achieved by ensuring that each input's associated display space and ease of…

In this study, we present synchronous bilingual Connectionist Temporal Classification (CTC), an innovative framework that leverages dual CTC to bridge the gaps of both modality and language in the speech translation (ST) task. Utilizing…

By incorporating additional contextual information, deep biasing methods have emerged as a promising solution for speech recognition of personalized words. However, for real-world voice assistants, always biasing on such personalized words…

Syntactic natural language parsers have shown themselves to be inadequate for processing highly-ambiguous large-vocabulary text, as is evidenced by their poor performance on domains like the Wall Street Journal, and by the movement away…

In this paper, we consider the problem of generalised visual object counting, with the goal of developing a computational model for counting the number of objects from arbitrary semantic categories, using arbitrary number of "exemplars",…

Disordered speech recognition profound implications for improving the quality of life for individuals afflicted with, for example, dysarthria. Dysarthric speech recognition encounters challenges including limited data, substantial…

We demonstrate that carefully adjusting the tokenizer of the Whisper speech recognition model significantly improves the precision of word-level timestamps when applying dynamic time warping to the decoder's cross-attention scores. We…

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…

Stroke is a major cause of mortality and long--term disability in the world. Predictive outcome models in stroke are valuable for personalized treatment, rehabilitation planning and in controlled clinical trials. In this paper we design a…

There exists an inordinate amount of spectral data in both public and private astronomical archives which remain severely under-utilised. The lack of reliable open-source tools for analysing large volumes of spectra contributes to this…

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…

Sign language is a gesture-based symbolic communication medium among speech and hearing impaired people. It also serves as a communication bridge between non-impaired and impaired populations. Unfortunately, in most situations, a…

Real-time captioning is a useful technique for deaf and hard-of-hearing (DHH) people to talk to hearing people. With the improvement in device performance and the accuracy of automatic speech recognition (ASR), real-time captioning is…

The goal of image style transfer is to render an image with artistic features guided by a style reference while maintaining the original content. Owing to the locality in convolutional neural networks (CNNs), extracting and maintaining the…

We study a novel multimodal-learning problem, which we call text matching: given an image containing a single-line text and a candidate text transcription, the goal is to assess whether the text represented in the image corresponds to the…

Conventional speech-to-text translation (ST) systems are trained on single-speaker utterances, and they may not generalize to real-life scenarios where the audio contains conversations by multiple speakers. In this paper, we tackle…

Token-based transformer world models have shown strong performance in visual reinforcement learning, but often suffer from temporal inconsistency in long-horizon rollouts, including object duplication, disappearance, and transmutation. A…

In recent years, end-to-end scene text spotting approaches are evolving to the Transformer-based framework. While previous studies have shown the crucial importance of the intrinsic synergy between text detection and recognition, recent…

Speech recognition performance varies by language, domain, and speaker characteristics such as accent, but fine-tuning a model on any of these categories may lead to catastrophic forgetting. Token-level $k$ nearest neighbor search ($k$NN),…