相关论文: LibriBrain: Over 50 Hours of Within-Subject MEG to…

Deep learning techniques have revolutionized the field of machine learning and were recently successfully applied to various classification problems in noninvasive electroencephalography (EEG). However, these methods were so far only rarely…

EEG is the most common signal source for noninvasive BCI applications. For such applications, the EEG signal needs to be decoded and translated into appropriate actions. A recently emerging EEG decoding approach is deep learning with…

Question answering is a natural language understanding task that involves reasoning over both explicit context, and unstated relevant domain knowledge. Despite the high cost of training, large language models (LLMs) -- the backbone of most…

Robust decoding and classification of brain patterns measured with electroencephalography (EEG) remains a major challenge for real-world (i.e. outside scientific lab and medical facilities) brain-computer interface (BCI) applications due to…

We present a corpus of sentence-aligned triples of German audio, German text, and English translation, based on German audiobooks. The speech translation data consist of 110 hours of audio material aligned to over 50k parallel sentences. An…

The evolving speech processing landscape is increasingly focused on complex scenarios like meetings or cocktail parties with multiple simultaneous speakers and far-field conditions. Existing methodologies for addressing these challenges…

Recent advances in deep learning based large vocabulary con- tinuous speech recognition (LVCSR) invoke growing demands in large scale speech transcription. The inference process of a speech recognizer is to find a sequence of labels whose…

Understanding how explicit theoretical features are encoded in opaque neural systems is a central challenge now common to neuroscience and AI. We introduce Metric Learning Encoding Models (MLEMs) to address this challenge most directly as a…

This technical report describes the MERaLiON-SpeechEncoder, a foundation model designed to support a wide range of downstream speech applications. Developed as part of Singapore's National Multimodal Large Language Model Programme, the…

Understanding how the human brain progresses from processing simple linguistic inputs to performing high-level reasoning is a fundamental challenge in neuroscience. While modern large language models (LLMs) are increasingly used to model…

Learning neural program embeddings is key to utilizing deep neural networks in program languages research --- precise and efficient program representations enable the application of deep models to a wide range of program analysis tasks.…

The human brain is constantly processing and integrating information in order to make decisions and interact with the world, for tasks from recognizing a familiar face to playing a game of tennis. These complex cognitive processes require…

Machine comprehension(MC) style question answering is a representative problem in natural language processing. Previous methods rarely spend time on the improvement of encoding layer, especially the embedding of syntactic information and…

Large-scale datasets have successively proven their fundamental importance in several research fields, especially for early progress in some emerging topics. In this paper, we focus on the problem of visual speech recognition, also known as…

Scientific reasoning is critical for developing AI scientists and supporting human researchers in advancing the frontiers of natural science discovery. However, the open-source community has primarily focused on mathematics and coding while…

Neural decoding from electroencephalography (EEG) remains fundamentally limited by poor generalization to unseen subjects, driven by high inter-subject variability and the lack of large-scale datasets to model it effectively. Existing…

Brain imaging data such as EEG or MEG are high-dimensional spatiotemporal data often degraded by complex, non-Gaussian noise. For reliable analysis of brain imaging data, it is important to extract discriminative, low-dimensional intrinsic…

We propose a fully convolutional sequence-to-sequence encoder architecture with a simple and efficient decoder. Our model improves WER on LibriSpeech while being an order of magnitude more efficient than a strong RNN baseline. Key to our…

Decoding human activity from EEG signals has long been a popular research topic. While recent studies have increasingly shifted focus from single-subject to cross-subject analysis, few have explored the model's ability to perform zero-shot…

Data-intensive applications, ranging from large-scale retrieval systems to advanced data pipelines, are increasingly bottlenecked by the processing of highly redundant text corpora. We present Merlin, a local-first, agnostic,…