Related papers: Joint Learning of Correlated Sequence Labelling Ta…

In this work, we describe a novel method of training an embedding-matching word-level connectionist temporal classification (CTC) automatic speech recognizer (ASR) such that it directly produces word start times and durations, required by…

Successful Machine Learning based Named Entity Recognition models could fail on texts from some special domains, for instance, Chinese addresses and e-commerce titles, where requires adequate background knowledge. Such texts are also…

End-to-end automatic speech recognition (ASR) models with a single neural network have recently demonstrated state-of-the-art results compared to conventional hybrid speech recognizers. Specifically, recurrent neural network transducer…

To let the state-of-the-art end-to-end ASR model enjoy data efficiency, as well as much more unpaired text data by multi-modal training, one needs to address two problems: 1) the synchronicity of feature sampling rates between speech and…

At the present time, computers are employed to solve complex tasks and problems ranging from simple calculations to intensive digital image processing and intricate algorithmic optimization problems to computationally-demanding weather…

We previously proposed contextual spelling correction (CSC) to correct the output of end-to-end (E2E) automatic speech recognition (ASR) models with contextual information such as name, place, etc. Although CSC has achieved reasonable…

In interactive automatic speech recognition (ASR) systems, low-latency requirements limit the amount of search space that can be explored during decoding, particularly in end-to-end neural ASR. In this paper, we present a novel streaming…

Effectively distinguishing the pronunciation correlations between different written texts is a significant issue in linguistic acoustics. Traditionally, such pronunciation correlations are obtained through manually designed pronunciation…

This paper proposed a class of novel Deep Recurrent Neural Networks which can incorporate language-level information into acoustic models. For simplicity, we named these networks Recurrent Deep Language Networks (RDLNs). Multiple variants…

While supervised learning models have shown remarkable performance in various natural language processing (NLP) tasks, their success heavily relies on the availability of large-scale labeled datasets, which can be costly and time-consuming…

Most Semantic Role Labeling (SRL) approaches are supervised methods which require a significant amount of annotated corpus, and the annotation requires linguistic expertise. In this paper, we propose a Multi-Task Active Learning framework…

The incorporation of biasing words obtained through contextual knowledge is of paramount importance in automatic speech recognition (ASR) applications. This paper proposes an innovative method for achieving end-to-end contextual ASR using…

This work focuses on the rapid development of linguistic annotation tools for resource-poor languages. We experiment several cross-lingual annotation projection methods using Recurrent Neural Networks (RNN) models. The distinctive feature…

Prevalent models based on artificial neural network (ANN) for sentence classification often classify sentences in isolation without considering the context in which sentences appear. This hampers the traditional sentence classification…

Large Language Models (LLMs) possess encompassing capabilities that can process diverse language-related tasks. However, finetuning on LLMs will diminish this general skills and continual finetuning will further cause severe degradation on…

Recurrent neural networks are a widely used class of neural architectures. They have, however, two shortcomings. First, it is difficult to understand what exactly they learn. Second, they tend to work poorly on sequences requiring long-term…

Segmentation for continuous Automatic Speech Recognition (ASR) has traditionally used silence timeouts or voice activity detectors (VADs), which are both limited to acoustic features. This segmentation is often overly aggressive, given that…

Dual learning is a paradigm for semi-supervised machine learning that seeks to leverage unsupervised data by solving two opposite tasks at once. In this scheme, each model is used to generate pseudo-labels for unlabeled examples that are…

While speech recognition Word Error Rate (WER) has reached human parity for English, long-form dictation scenarios still suffer from segmentation and punctuation problems resulting from irregular pausing patterns or slow speakers.…

In this paper we study different types of Recurrent Neural Networks (RNN) for sequence labeling tasks. We propose two new variants of RNNs integrating improvements for sequence labeling, and we compare them to the more traditional Elman and…