Related papers: Independent-Component-Based Encoding Models of Bra…
Independent Component Analysis (ICA) offers interpretable semantic components of embeddings. While ICA theory assumes that embeddings can be linearly decomposed into independent components, real-world data often do not satisfy this…
Speech signals encompass various information across multiple levels including content, speaker, and style. Disentanglement of these information, although challenging, is important for applications such as voice conversion. The contrastive…
This article introduces a predictor-dependent joint modeling framework for network data obtained from multiple subjects over a shared set of nodes with spatial co-ordinates and spatially correlated nodal attributes. The framework is highly…
Time-encoding of continuous-time signals is an alternative sampling paradigm to conventional methods such as Shannon's sampling. In time-encoding, the signal is encoded using a sequence of time instants where an event occurs, and hence fall…
Our investigation into the Affective Reasoning in Conversation (ARC) task highlights the challenge of causal discrimination. Almost all existing models, including large language models (LLMs), excel at capturing semantic correlations within…
Electroencephalography (EEG) measures the electrical brain activity in real-time by using sensors placed on the scalp. Artifacts, due to eye movements and blink, muscular/cardiac activity and generic electrical disturbances, have to be…
To extract robust deep representations from long sequential modeling of speech data, we propose a self-supervised learning approach, namely Contrastive Separative Coding (CSC). Our key finding is to learn such representations by separating…
Objective: This work aims to demonstrate a low-power, biomimetic auditory sensing concept for fully implantable cochlear implants. The approach draws inspiration from the frequency selectivity and temporal encoding of the cochlea, and uses…
We present a sequential transfer learning framework for transformers on functional Magnetic Resonance Imaging (fMRI) data and demonstrate its significant benefits for decoding musical timbre. In the first of two phases, we pre-train our…
We present an audio-visual speech separation learning method that considers the correspondence between the separated signals and the visual signals to reflect the speech characteristics during training. Audio-visual speech separation is a…
Non-invasive brainwave decoding is usually done using Magneto/Electroencephalography (MEG/EEG) sensor measurements as inputs. This makes combining datasets and building models with inductive biases difficult as most datasets use different…
We consider exploratory methods for the discovery of cortical functional connectivity. Typically, data for the i-th subject (i=1...NS) is represented as an NVxNT matrix Xi, corresponding to brain activity sampled at NT moments in time from…
Automated discourse analysis tools based on Natural Language Processing (NLP) aiming at the diagnosis of language-impairing dementias generally extract several textual metrics of narrative transcripts. However, the absence of sentence…
Independent component analysis (ICA) is a statistical method for transforming an observable multi-dimensional random vector into components that are as statistically independent as possible from each other. Usually the ICA framework assumes…
Sparse coding is an unsupervised learning algorithm that learns a succinct high-level representation of the inputs given only unlabeled data; it represents each input as a sparse linear combination of a set of basis functions. Originally…
Implicit Neural Representations (INRs) have revolutionized signal representation by leveraging neural networks to provide continuous and smooth representations of complex data. However, existing INRs face limitations in capturing…
The development of foundation models for functional magnetic resonance imaging (fMRI) time series holds significant promise for predicting phenotypes related to disease and cognition. Current models, however, are often trained using a…
The correlated variability in the responses of a neural population to the repeated presentation of a sensory stimulus is a universally observed phenomenon. Such correlations have been studied in much detail, both with respect to their…
In this work, we investigate the time series representation learning problem using self-supervised techniques. Contrastive learning is well-known in this area as it is a powerful method for extracting information from the series and…
Automated audio captioning (AAC) has developed rapidly in recent years, involving acoustic signal processing and natural language processing to generate human-readable sentences for audio clips. The current models are generally based on the…