Related papers: Brain-to-Text Benchmark '24: Lessons Learned

Much recent progress in Vision-to-Language problems has been achieved through a combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). This approach does not explicitly represent high-level semantic…

Interpretability techniques are valuable for helping humans understand and oversee AI systems. The SaTML 2024 CNN Interpretability Competition solicited novel methods for studying convolutional neural networks (CNNs) at the ImageNet scale.…

The ConferencingSpeech 2021 challenge is proposed to stimulate research on far-field multi-channel speech enhancement for video conferencing. The challenge consists of two separate tasks: 1) Task 1 is multi-channel speech enhancement with…

Language, as an information medium created by advanced organisms, has always been a concern of neuroscience regarding how it is represented in the brain. Decoding linguistic representations in the evoked brain has shown groundbreaking…

Humans learn language by interaction with their environment and listening to other humans. It should also be possible for computational models to learn language directly from speech but so far most approaches require text. We improve on…

Modern compression algorithms are often the result of laborious domain-specific research; industry standards such as MP3, JPEG, and AMR-WB took years to develop and were largely hand-designed. We present a deep neural network model which…

With the increasing prevalence of text generated by large language models (LLMs), there is a growing concern about distinguishing between LLM-generated and human-written texts in order to prevent the misuse of LLMs, such as the…

End-to-end neural TTS training has shown improved performance in speech style transfer. However, the improvement is still limited by the training data in both target styles and speakers. Inadequate style transfer performance occurs when the…

Direct speech-to-text translation systems encounter an important drawback in data scarcity. A common solution consists on pretraining the encoder on automatic speech recognition, hence losing efficiency in the training process. In this…

Neural networks have recently achieved human-level performance on various challenging natural language processing (NLP) tasks, but it is notoriously difficult to understand why a neural network produced a particular prediction. In this…

We study the pre-train + fine-tune strategy for data-to-text tasks. Our experiments indicate that text-to-text pre-training in the form of T5, enables simple, end-to-end transformer based models to outperform pipelined neural architectures…

The decoding of continuously spoken speech from neuronal activity has the potential to become an important clinical solution for paralyzed patients. Deep Learning Brain Computer Interfaces (BCIs) have recently successfully mapped neuronal…

The state of the art in learning meaningful semantic representations of words is the Transformer model and its attention mechanisms. Simply put, the attention mechanisms learn to attend to specific parts of the input dispensing recurrence…

A fundamental ability of humans is to utilize commonsense knowledge in language understanding and question answering. In recent years, many knowledge-enhanced Commonsense Question Answering (CQA) approaches have been proposed. However, it…

Existing methods to measure sentence similarity are faced with two challenges: (1) labeled datasets are usually limited in size, making them insufficient to train supervised neural models; (2) there is a training-test gap for unsupervised…

Speech emotion recognition is a challenging task and an important step towards more natural human-machine interaction. We show that pre-trained language models can be fine-tuned for text emotion recognition, achieving an accuracy of 69.5%…

Despite the ubiquity of mobile and wearable text messaging applications, the problem of keyboard text decoding is not tackled sufficiently in the light of the enormous success of the deep learning Recurrent Neural Network (RNN) and…

Subword tokenization is a commonly used input pre-processing step in most recent NLP models. However, it limits the models' ability to leverage end-to-end task learning. Its frequency-based vocabulary creation compromises tokenization in…

Speech clarity and spatial audio immersion are the two most critical factors in enhancing remote conferencing experiences. Existing methods are often limited: either due to the lack of spatial information when using only one microphone, or…

This paper presents a method of sequence-to-sequence (seq2seq) voice conversion using non-parallel training data. In this method, disentangled linguistic and speaker representations are extracted from acoustic features, and voice conversion…