Related papers: Are EEG-to-Text Models Working?

As the use of text-to-image generative models increases, so does the adoption of automatic benchmarking methods used in their evaluation. However, while metrics and datasets abound, there are few unified benchmarking libraries that provide…

Recently, several data-sets associating data to text have been created to train data-to-text surface realisers. It is unclear however to what extent the surface realisation task exercised by these data-sets is linguistically challenging. Do…

In this paper, we propose an end-to-end neural network (NN) based EEG-speech (NES) modeling framework, in which three network structures are developed to map imagined EEG signals to phonemes. The proposed NES models incorporate a language…

Transfer learning, where a model is first pre-trained on a data-rich task before being fine-tuned on a downstream task, has emerged as a powerful technique in natural language processing (NLP). The effectiveness of transfer learning has…

We present a method for introducing a text encoder into pre-trained end-to-end speech translation systems. It enhances the ability of adapting one modality (i.e., source-language speech) to another (i.e., source-language text). Thus, the…

State-of-the-art speech synthesis models try to get as close as possible to the human voice. Hence, modelling emotions is an essential part of Text-To-Speech (TTS) research. In our work, we selected FastSpeech2 as the starting point and…

Clinical brain-to-text interfaces are designed for paralysed patients who cannot provide extensive training recordings. Pre-training improves data-efficient generalisation by learning statistical priors across subjects, but these priors…

We describe models focused at the understudied problem of translating between monolingual and code-mixed language pairs. More specifically, we offer a wide range of models that convert monolingual English text into Hinglish (code-mixed…

In most cases, the lack of parallel corpora makes it impossible to directly train supervised models for the text style transfer task. In this paper, we explore training algorithms that instead optimize reward functions that explicitly…

Electroencephalography (EEG) is a generally used neuroimaging approach in brain-computer interfaces due to its non-invasive characteristics and convenience, making it an effective tool for understanding human intentions. Therefore, recent…

Speaker-dependent modelling can substantially improve performance in speech-based health monitoring applications. While mixed-effect models are commonly used for such speaker adaptation, they require computationally expensive retraining for…

Speech-to-Speech Translation (S2ST) models transform speech from one language to another target language with the same linguistic information. S2ST is important for bridging the communication gap among communities and has diverse…

We introduce EmphAssess, a prosodic benchmark designed to evaluate the capability of speech-to-speech models to encode and reproduce prosodic emphasis. We apply this to two tasks: speech resynthesis and speech-to-speech translation. In both…

Electroencephalography (EEG) is commonly used by physicians for the diagnosis of numerous neurological disorders. Due to the large volume of EEGs requiring interpretation and the specific expertise involved, artificial intelligence-based…

Data Visualization has been receiving growing attention recently, with ubiquitous smart devices designed to render information in a variety of ways. However, while evaluations of visual tools for their interpretability and intuitiveness…

Nowadays, machine and deep learning techniques are widely used in different areas, ranging from economics to biology. In general, these techniques can be used in two ways: trying to adapt well-known models and architectures to the available…

The advancements in deep learning, particularly the introduction of transformers, have been pivotal in enhancing various natural language processing (NLP) tasks. These include text-to-text applications such as machine translation, text…

Text classification tasks which aim at harvesting and/or organizing information from electronic health records are pivotal to support clinical and translational research. However these present specific challenges compared to other…

Machine unlearning aims to remove sensitive or undesired data from large language models. However, recent studies suggest that unlearning is often shallow, claiming that removed knowledge can easily be recovered. In this work, we critically…

Can continuous diffusion models bring the same performance breakthrough on natural language they did for image generation? To circumvent the discrete nature of text data, we can simply project tokens in a continuous space of embeddings, as…