Related papers: Spatial Attention and Syntax Rule Enhanced Tree De…

The paper presents a method for spoken term detection based on the Transformer architecture. We propose the encoder-encoder architecture employing two BERT-like encoders with additional modifications, including convolutional and upsampling…

This paper investigates the framework of encoder-decoder with attention for sequence labelling based spoken language understanding. We introduce Bidirectional Long Short Term Memory - Long Short Term Memory networks (BLSTM-LSTM) as the…

The task of recognising Handwritten Mathematical Expressions (HMER) is crucial in the fields of digital education and scholarly research. However, it is difficult to accurately determine the length and complex spatial relationships among…

ICD coding is designed to assign the disease codes to electronic health records (EHRs) upon discharge, which is crucial for billing and clinical statistics. In an attempt to improve the effectiveness and efficiency of manual coding, many…

Handwriting recognition has seen significant success with the use of deep learning. However, a persistent shortcoming of neural networks is that they are not well-equipped to deal with shifting data distributions. In the field of…

Speech Emotion Recognition (SER) has been traditionally formulated as a classification task. However, emotions are generally a spectrum whose distribution varies from situation to situation leading to poor Out-of-Domain (OOD) performance.…

Transformer-based models have demonstrated significant success in various source code representation tasks. Nonetheless, traditional positional embeddings employed by these models inadequately capture the hierarchical structure intrinsic to…

While speaking at different rates, articulators (like tongue, lips) tend to move differently and the enunciations are also of different durations. In the past, affine transformation and DNN have been used to transform articulatory movements…

In this work we propose a novel token-based training strategy that improves Transformer-Transducer (T-T) based speaker change detection (SCD) performance. The conventional T-T based SCD model loss optimizes all output tokens equally. Due to…

Scaled dot-product attention applies a softmax function on the scaled dot-product of queries and keys to calculate weights and then multiplies the weights and values. In this work, we study how to improve the learning of scaled dot-product…

We replace the Hidden Markov Model (HMM) which is traditionally used in in continuous speech recognition with a bi-directional recurrent neural network encoder coupled to a recurrent neural network decoder that directly emits a stream of…

Depression is a common mental disorder. Automatic depression detection tools using speech, enabled by machine learning, help early screening of depression. This paper addresses two limitations that may hinder the clinical implementations of…

Handwritten mathematical expression recognition aims to automatically generate LaTeX sequences from given images. Currently, attention-based encoder-decoder models are widely used in this task. They typically generate target sequences in a…

To safeguard machine learning systems that operate on textual data against out-of-distribution (OOD) inputs that could cause unpredictable behaviour, we explore the use of topological features of self-attention maps from transformer-based…

Predicting high-dimensional dynamical systems with irregular time steps presents significant challenges for current data-driven algorithms. These irregularities arise from missing data, sparse observations, or adaptive computational…

Precise geocoding and time normalization for text requires that location and time phrases be identified. Many state-of-the-art geoparsers and temporal parsers suffer from low recall. Categories commonly missed by parsers are: nouns used in…

Detecting out-of-scope user utterances is essential for task-oriented dialogues and intent classification. Current methodologies face difficulties with the unpredictable distribution of outliers and often rely on assumptions about data…

Semantic role labeling (SRL), also known as shallow semantic parsing, is an important yet challenging task in NLP. Motivated by the close correlation between syntactic and semantic structures, traditional discrete-feature-based SRL…

Building models that take advantage of the hierarchical structure of language without a priori annotation is a longstanding goal in natural language processing. We introduce such a model for the task of machine translation, pairing a…

Self-supervised learning (SSL) has shown tremendous success in various speech-related downstream tasks, including Automatic Speech Recognition (ASR). The output embeddings of the SSL model are treated as powerful short-time representations…