Self-supervised speech models can be trained to efficiently recognize spoken words in naturalistic, noisy environments.However, we do not understand the types of linguistic representations these models use to accomplish this task.To address this question, we study how S3M variants optimized for word recognition represent phonological and morphological phenomena in frequent English noun and verb inflections.We find that their representations exhibit a global linear geometry which can be used to link English nouns and verbs to their regular inflected forms.This geometric structure does not directly track phonological or morphological units.Instead, it tracks the regular distributional relationships linking many word pairs in the English lexicon-often, but not always, due to morphological inflection.These findings point to candidate representational strategies that may support human spoken word recognition, challenging the presumed necessity of distinct linguistic representations of phonology and morphology.

Speech and language models trained through self-supervised learning (SSL) demonstrate strong alignment with brain activity during speech and language perception. However, given their distinct training modalities, it remains unclear whether they correlate with the same neural aspects. We directly address this question by evaluating the brain prediction performance of two representative SSL models, Wav2Vec2.0 and GPT-2, designed for speech and language tasks. Our findings reveal that both models accurately predict speech responses in the auditory cortex, with a significant correlation between their brain predictions. Notably, shared speech contextual information between Wav2Vec2.0 and GPT-2 accounts for the majority of explained variance in brain activity, surpassing static semantic and lower-level acoustic-phonetic information. These results underscore the convergence of speech contextual representations in SSL models and their alignment with the neural network underlying speech perception, offering valuable insights into both SSL models and the neural basis of speech and language processing.

Reconstructing natural speech from neural activity is vital for enabling direct communication via brain-computer interfaces. Previous efforts have explored the conversion of neural recordings into speech using complex deep neural network (DNN) models trained on extensive neural recording data, which is resource-intensive under regular clinical constraints. However, achieving satisfactory performance in reconstructing speech from limited-scale neural recordings has been challenging, mainly due to the complexity of speech representations and the neural data constraints. To overcome these challenges, we propose a novel transfer learning framework for neural-driven speech reconstruction, called Neural2Speech, which consists of two distinct training phases. First, a speech autoencoder is pre-trained on readily available speech corpora to decode speech waveforms from the encoded speech representations. Second, a lightweight adaptor is trained on the small-scale neural recordings to align the neural activity and the speech representation for decoding. Remarkably, our proposed Neural2Speech demonstrates the feasibility of neural-driven speech reconstruction even with only 20 minutes of intracranial data, which significantly outperforms existing baseline methods in terms of speech fidelity and intelligibility.

Understanding the neural implementation of complex human behaviors is one of the major goals in neuroscience. To this end, it is crucial to find a true representation of the neural data, which is challenging due to the high complexity of behaviors and the low signal-to-ratio (SNR) of the signals. Here, we propose a novel unsupervised learning framework, Neural Latent Aligner (NLA), to find well-constrained, behaviorally relevant neural representations of complex behaviors. The key idea is to align representations across repeated trials to learn cross-trial consistent information. Furthermore, we propose a novel, fully differentiable time warping model (TWM) to resolve the temporal misalignment of trials. When applied to intracranial electrocorticography (ECoG) of natural speaking, our model learns better representations for decoding behaviors than the baseline models, especially in lower dimensional space. The TWM is empirically validated by measuring behavioral coherence between aligned trials. The proposed framework learns more cross-trial consistent representations than the baselines, and when visualized, the manifold reveals shared neural trajectories across trials.

A ubiquitous problem in aggregating data across different experimental and observational data sources is a lack of software infrastructure that enables flexible and extensible standardization of data and metadata. To address this challenge, we developed HDMF, a hierarchical data modeling framework for modern science data standards. With HDMF, we separate the process of data standardization into three main components: (1) data modeling and specification, (2) data I/O and storage, and (3) data interaction and data APIs. To enable standards to support the complex requirements and varying use cases throughout the data life cycle, HDMF provides object mapping infrastructure to insulate and integrate these various components. This approach supports the flexible development of data standards and extensions, optimized storage backends, and data APIs, while allowing the other components of the data standards ecosystem to remain stable. To meet the demands of modern, large-scale science data, HDMF provides advanced data I/O functionality for iterative data write, lazy data load, and parallel I/O. It also supports optimization of data storage via support for chunking, compression, linking, and modular data storage. We demonstrate the application of HDMF in practice to design NWB 2.0 [13], a modern data standard for collaborative science across the neurophysiology community.

A fundamental challenge in neuroscience is to understand what structure in the world is represented in spatially distributed patterns of neural activity from multiple single-trial measurements. This is often accomplished by learning a simple, linear transformations between neural features and features of the sensory stimuli or motor task. While successful in some early sensory processing areas, linear mappings are unlikely to be ideal tools for elucidating nonlinear, hierarchical representations of higher-order brain areas during complex tasks, such as the production of speech by humans. Here, we apply deep networks to predict produced speech syllables from a dataset of high gamma cortical surface electric potentials recorded from human sensorimotor cortex. We find that deep networks had higher decoding prediction accuracy compared to baseline models. Having established that deep networks extract more task relevant information from neural data sets relative to linear models (i.e., higher predictive accuracy), we next sought to demonstrate their utility as a data analysis tool for neuroscience. We first show that deep network's confusions revealed hierarchical latent structure in the neural data, which recapitulated the underlying articulatory nature of speech motor control. We next broadened the frequency features beyond high-gamma and identified a novel high-gamma-to-beta coupling during speech production. Finally, we used deep networks to compare task-relevant information in different neural frequency bands, and found that the high-gamma band contains the vast majority of information relevant for the speech prediction task, with little-to-no additional contribution from lower-frequency amplitudes. Together, these results demonstrate the utility of deep networks as a data analysis tool for basic and applied neuroscience.

The increasing size and complexity of scientific data could dramatically enhance discovery and prediction for basic scientific applications, e.g., neuroscience, genetics, systems biology, etc. Realizing this potential, however, requires novel statistical analysis methods that are both interpretable and predictive. We introduce the Union of Intersections (UoI) method, a flexible, modular, and scalable framework for enhanced model selection and estimation. The method performs model selection and model estimation through intersection and union operations, respectively. We show that UoI can satisfy the bi-criteria of low-variance and nearly unbiased estimation of a small number of interpretable features, while maintaining high-quality prediction accuracy. We perform extensive numerical investigation to evaluate a UoI algorithm ($UoI_{Lasso}$) on synthetic and real data. In doing so, we demonstrate the extraction of interpretable functional networks from human electrophysiology recordings as well as the accurate prediction of phenotypes from genotype-phenotype data with reduced features. We also show (with the $UoI_{L1Logistic}$ and $UoI_{CUR}$ variants of the basic framework) improved prediction parsimony for classification and matrix factorization on several benchmark biomedical data sets. These results suggest that methods based on UoI framework could improve interpretation and prediction in data-driven discovery across scientific fields.

BACKGROUND: There exists a need for effective and easy-to-use software tools supporting the analysis of complex Electrocorticography (ECoG) data. Understanding how epileptic seizures develop or identifying diagnostic indicators for neurological diseases require the in-depth analysis of neural activity data from ECoG. Such data is multi-scale and is of high spatio-temporal resolution. Comprehensive analysis of this data should be supported by interactive visual analysis methods that allow a scientist to understand functional patterns at varying levels of granularity and comprehend its time-varying behavior. RESULTS: We introduce a novel multi-scale visual analysis system, ECoG ClusterFlow, for the detailed exploration of ECoG data. Our system detects and visualizes dynamic high-level structures, such as communities, derived from the time-varying connectivity network. The system supports two major views: 1) an overview summarizing the evolution of clusters over time and 2) an electrode view using hierarchical glyph-based design to visualize the propagation of clusters in their spatial, anatomical context. We present case studies that were performed in collaboration with neuroscientists and neurosurgeons using simulated and recorded epileptic seizure data to demonstrate our system's effectiveness. CONCLUSION: ECoG ClusterFlow supports the comparison of spatio-temporal patterns for specific time intervals and allows a user to utilize various clustering algorithms. Neuroscientists can identify the site of seizure genesis and its spatial progression during various the stages of a seizure. Our system serves as a fast and powerful means for the generation of preliminary hypotheses that can be used as a basis for subsequent application of rigorous statistical methods, with the ultimate goal being the clinical treatment of epileptogenic zones.