相关论文: Unlocking Non-Invasive Brain-to-Text

Neuroimaging studies are often limited by the number of subjects and cognitive processes that can be feasibly interrogated. However, a rapidly growing number of neuroscientific studies have collectively accumulated an extensive wealth of…

Non-invasive brain-computer interfaces that decode spoken commands from electroencephalogram must be both accurate and trustworthy. We present a confidence-aware decoding framework that couples deep ensembles of compact, speech-oriented…

Recent end-to-end task oriented dialog systems use memory architectures to incorporate external knowledge in their dialogs. Current work makes simplifying assumptions about the structure of the knowledge base, such as the use of triples to…

Speech Brain Computer Interfaces (BCIs) offer promising solutions to people with severe paralysis unable to communicate. A number of recent studies have demonstrated convincing reconstruction of intelligible speech from surface…

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…

Deepspeech was very useful for development IoT devices that need voice recognition. One of the voice recognition systems is deepspeech from Mozilla. Deepspeech is an open-source voice recognition that was using a neural network to convert…

We introduce the Byte Latent Transformer (BLT), a new byte-level LLM architecture that, for the first time, matches tokenization-based LLM performance at scale with significant improvements in inference efficiency and robustness. BLT…

Pre-trained large language models have recently achieved ground-breaking performance in a wide variety of language understanding tasks. However, the same model can not be applied to multimodal behavior understanding tasks (e.g., video…

Bilingual Lexicon Induction (BLI) is a core task in multilingual NLP that still, to a large extent, relies on calculating cross-lingual word representations. Inspired by the global paradigm shift in NLP towards Large Language Models (LLMs),…

Every day, the human brain processes an immense volume of visual information, relying on intricate neural mechanisms to perceive and interpret these stimuli. Recent breakthroughs in functional magnetic resonance imaging (fMRI) have enabled…

Recent advances in generative AI have been largely driven by large language models (LLMs), deep neural networks that operate over discrete units called tokens. To represent text, the vast majority of LLMs use words or word fragments as the…

Brain-to-Image reconstruction aims to recover visual stimuli perceived by humans from brain activity. However, the reconstructed visual stimuli often missing details and semantic inconsistencies, which may be attributed to insufficient…

Language models (LMs) are pre-trained on raw text datasets to generate text sequences token-by-token. While this approach facilitates the learning of world knowledge and reasoning, it does not explicitly optimize for linguistic competence.…

Current research in speech-to-speech translation (S2ST) primarily concentrates on translation accuracy and speech naturalness, often overlooking key elements like paralinguistic information, which is essential for conveying emotions and…

The paper reviews and summarizes recent developments in spatial auditory and tactile brain-computer interfacing neurotechology applications. It serves as the latest developments summary in "non-visual" brain-computer interfacing solutions…

The lack of speech data annotated with labels required for spoken language understanding (SLU) is often a major hurdle in building end-to-end (E2E) systems that can directly process speech inputs. In contrast, large amounts of text data…

Autoregressive Sequence-To-Sequence models are the foundation of many Deep Learning achievements in major research fields such as Vision and Natural Language Processing. Despite that, they still present significant limitations. For…

Brain-computer interfaces (BCIs) for speech restoration hold transformative potential for the approximately 173,000--232,500 individuals worldwide with ALS-related dysarthria. Despite recent progress, high-performance speech BCIs have been…

Restoring speech communication from neural signals is a central goal of brain-computer interface research, yet EEG-based speech reconstruction remains challenging due to limited spatial resolution, susceptibility to noise, and the absence…

Speech language models (SpeechLMs) accept speech input and produce speech output, allowing for more natural human-computer interaction compared to text-based large language models (LLMs). Traditional approaches for developing SpeechLMs are…