Related papers: Context-aware Fine-tuning of Self-supervised Speec…

We propose a cross-modal transformer-based neural correction models that refines the output of an automatic speech recognition (ASR) system so as to exclude ASR errors. Generally, neural correction models are composed of encoder-decoder…

In-context learning enables language models (LM) to adapt to downstream data or tasks by incorporating few samples as demonstrations within the prompts. It offers strong performance without the expense of fine-tuning. However, the…

Some autoregressive models exhibit in-context learning capabilities: being able to learn as an input sequence is processed, without undergoing any parameter changes, and without being explicitly trained to do so. The origins of this…

Fine-tuning pre-trained contextualized embedding models has become an integral part of the NLP pipeline. At the same time, probing has emerged as a way to investigate the linguistic knowledge captured by pre-trained models. Very little is,…

Finetuning is a common practice widespread across different communities to adapt pretrained models to particular tasks. Text classification is one of these tasks for which many pretrained models are available. On the other hand, ensembles…

Self-supervised learning (SSL) is a powerful tool that allows learning of underlying representations from unlabeled data. Transformer based models such as wav2vec 2.0 and HuBERT are leading the field in the speech domain. Generally these…

A variety of contextualised language models have been proposed in the NLP community, which are trained on diverse corpora to produce numerous Neural Language Models (NLMs). However, different NLMs have reported different levels of…

There is a lot of research interest in encoding variable length sentences into fixed length vectors, in a way that preserves the sentence meanings. Two common methods include representations based on averaging word vectors, and…

Conversational speech, while being unstructured at an utterance level, typically has a macro topic which provides larger context spanning multiple utterances. The current language models in speech recognition systems using recurrent neural…

We investigate the use of extended context in attention-based neural machine translation. We base our experiments on translated movie subtitles and discuss the effect of increasing the segments beyond single translation units. We study the…

The ability to acquire latent semantics is one of the key properties that determines the performance of language models. One convenient approach to invoke this ability is to prepend metadata (e.g. URLs, domains, and styles) at the beginning…

Speech enhancement plays an essential role in various applications, and the integration of visual information has been demonstrated to bring substantial advantages. However, the majority of current research concentrates on the examination…

Pretrained visual-language models have extensive world knowledge and are widely used in visual and language navigation (VLN). However, they are not sensitive to indoor scenarios for VLN tasks. Another challenge for VLN is how the agent…

Language models can learn sophisticated language understanding skills from fitting raw text. They also unselectively learn useless corpus statistics and biases, especially during finetuning on domain-specific corpora. In this paper, we…

With the development of deep learning, neural network-based speech enhancement (SE) models have shown excellent performance. Meanwhile, it was shown that the development of self-supervised pre-trained models can be applied to various…

Context faithfulness is essential for reliable reasoning in context-dependent scenarios. However, large language models often struggle to ground their outputs in the provided context, resulting in irrelevant responses. Inspired by the…

In the domain adaptation problem, source data may be unavailable to the target client side due to privacy or intellectual property issues. Source-free unsupervised domain adaptation (SF-UDA) aims at adapting a model trained on the source…

The recently proposed self-attentive pooling (SAP) has shown good performance in several speaker recognition systems. In SAP systems, the context vector is trained end-to-end together with the feature extractor, where the role of context…

The pretrain-finetune paradigm usually improves downstream performance over training a model from scratch on the same task, becoming commonplace across many areas of machine learning. While pretraining is empirically observed to be…

Fine-tuning is widely used as the default algorithm for transfer learning from pre-trained models. Parameter inefficiency can however arise when, during transfer learning, all the parameters of a large pre-trained model need to be updated…