相关论文: From Minutes to Days: Scaling Intracranial Speech …

We provide an empirical investigation of the potential of pre-training vision-language models on an unprecedented scale: 100 billion examples. We find that model performance tends to saturate at this scale on many common Western-centric…

Artificial neural networks are increasingly powerful models of brain computation, yet it remains unclear whether improving their performance in downstream tasks also makes their internal representations more similar to brain signals. To…

Electroencephalography (EEG) decoding is a challenging task due to the limited availability of labelled data. While transfer learning is a promising technique to address this challenge, it assumes that transferable data domains and task are…

It has been generally assumed in the automatic speech recognition (ASR) literature that it is better for models to have access to wider context windows. Yet, many of the potential reasons this might be true in the supervised setting do not…

Accurately detecting voiced intervals in speech signals is a critical step in pitch tracking and has numerous applications. While conventional signal processing methods and deep learning algorithms have been proposed for this task, their…

We create a reusable Transformer, BrainBERT, for intracranial recordings bringing modern representation learning approaches to neuroscience. Much like in NLP and speech recognition, this Transformer enables classifying complex concepts,…

Reasoning is an integral part of many tasks performed by language models (LMs). However, the effects of scaling model sizes and data on reasoning abilities at pretraining time remain understudied. To rigorously investigate this problem, we…

Contrastive pretraining on image-text pairs from the web is one of the most popular large-scale pretraining strategies for vision backbones, especially in the context of large multimodal models. At the same time, image captioning on this…

We propose a Perceiver-based sequence classifier to detect abnormalities in speech reflective of several neurological disorders. We combine this classifier with a Universal Speech Model (USM) that is trained (unsupervised) on 12 million…

Brain decoding is a field of computational neuroscience that uses measurable brain activity to infer mental states or internal representations of perceptual inputs. Therefore, we propose a novel approach to brain decoding that also relies…

Cognitive neuroscience is enjoying rapid increase in extensive public brain-imaging datasets. It opens the door to large-scale statistical models. Finding a unified perspective for all available data calls for scalable and automated…

Representations from transformer-based unidirectional language models are known to be effective at predicting brain responses to natural language. However, most studies comparing language models to brains have used GPT-2 or similarly sized…

Visual brain decoding aims to decode visual information from human brain activities. Despite the great progress, one critical limitation of current brain decoding research lies in the lack of generalization capability to unseen subjects.…

We propose an approach for pre-training speech representations via a masked reconstruction loss. Our pre-trained encoder networks are bidirectional and can therefore be used directly in typical bidirectional speech recognition models. The…

Specialized foundation models are beginning to emerge in various medical subdomains, but pretraining methodologies and parametric scaling with the size of the pretraining dataset are rarely assessed systematically and in a like-for-like…

Brain-computer interface uses brain signals to control external devices without actual control behavior. Recently, speech imagery has been studied for direct communication using language. Speech imagery uses brain signals generated when the…

Generative models have gained more and more attention in recent years for their remarkable success in tasks that required estimating and sampling data distribution to generate high-fidelity synthetic data. In speech, text-to-speech…

We propose an approach for cognitive coding of speech by unsupervised extraction of contextual representations in two hierarchical levels of abstraction. Speech attributes such as phoneme identity that last one hundred milliseconds or less…

Neuroscientists today can measure activity from more neurons than ever before, and are facing the challenge of connecting these brain-wide neural recordings to computation and behavior. Here, we first describe emerging tools and…

Language models achieve impressive performance on a variety of knowledge, language, and reasoning tasks due to the scale and diversity of pretraining data available. The standard training recipe is a two-stage paradigm: pretraining first on…