Related papers: Multilingual Contextual Adapters To Improve Custom…

Pretrained multilingual contextual representations have shown great success, but due to the limits of their pretraining data, their benefits do not apply equally to all language varieties. This presents a challenge for language varieties…

Automatic speech recognition systems have been largely improved in the past few decades and current systems are mainly hybrid-based and end-to-end-based. The recently proposed CTC-CRF framework inherits the data-efficiency of the hybrid…

In Automatic Speech Recognition it is still challenging to learn useful intermediate representations when using high-level (or abstract) target units such as words. For that reason, character or phoneme based systems tend to outperform…

In topic identification (topic ID) on real-world unstructured audio, an audio instance of variable topic shifts is first broken into sequential segments, and each segment is independently classified. We first present a general purpose…

Large Language Models (LLMs) possess remarkable generalization capabilities but struggle with multi-task adaptation, particularly in balancing knowledge retention with task-specific specialization. Conventional fine-tuning methods suffer…

This research identifies a gap in weakly-labelled multivariate time-series classification (TSC), where state-of-the-art TSC models do not per-form well. Weakly labelled time-series are time-series containing noise and significant…

The development of state-of-the-art generative large language models (LLMs) disproportionately relies on English-centric tokenizers, vocabulary and pre-training data. Despite the fact that some LLMs have multilingual capabilities, recent…

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…

We consider feature learning for efficient keyword spotting that can be applied in severely under-resourced settings. The objective is to support humanitarian relief programmes by the United Nations in parts of Africa in which almost no…

Neural transducer is now the most popular end-to-end model for speech recognition, due to its naturally streaming ability. However, it is challenging to adapt it with text-only data. Factorized neural transducer (FNT) model was proposed to…

In recent years, learned image compression (LIC) technologies have surpassed conventional methods notably in terms of rate-distortion (RD) performance. Most present learned techniques are VAE-based with an autoregressive entropy model,…

Self-attention model have shown its flexibility in parallel computation and the effectiveness on modeling both long- and short-term dependencies. However, it calculates the dependencies between representations without considering the…

This paper explores the use of Hybrid CTC/Attention encoder-decoder models trained with Intermediate CTC (InterCTC) for Irish (Gaelic) low-resource speech recognition (ASR) and dialect identification (DID). Results are compared to the…

Despite the recent developments in the field of cross-modal retrieval, there has been less research focusing on low-resource languages due to the lack of manually annotated datasets. In this paper, we propose a noise-robust cross-lingual…

The "massively-multilingual" training of multilingual models is known to limit their utility in any one language, and they perform particularly poorly on low-resource languages. However, there is evidence that low-resource languages can…

The goal of accent conversion (AC) is to convert speech accents while preserving content and speaker identity. Previous methods either required reference utterances during inference, did not preserve speaker identity well, or used…

Multi-Task Learning (MTL) networks have emerged as a promising method for transferring learned knowledge across different tasks. However, MTL must deal with challenges such as: overfitting to low resource tasks, catastrophic forgetting, and…

Non-autoregressive (NAR) models for automatic speech recognition (ASR) aim to achieve high accuracy and fast inference by simplifying the autoregressive (AR) generation process of conventional models. Connectionist temporal classification…

The development of resource-constrained approaches to automatic speech recognition (ASR) is of great interest due to its broad applicability to many low-resource languages for which there is scant usable data. Existing approaches to many…

This paper studies a text classification algorithm based on an improved Transformer to improve the performance and efficiency of the model in text classification tasks. Aiming at the shortcomings of the traditional Transformer model in…