相关论文: Sparse Codes for Speech Predict Spectrotemporal Re…

Complex-valued sparse coding is a data representation which employs a dictionary of two-dimensional subspaces, while imposing a sparse, factorial prior on complex amplitudes. When trained on a dataset of natural image patches, it learns…

To date a number of studies have shown that receptive field shapes of early sensory neurons can be reproduced by optimizing coding efficiency of natural stimulus ensembles. A still unresolved question is whether the efficient coding…

Interaction with the world requires an organism to transform sensory signals into representations in which behaviorally meaningful properties of the environment are made explicit. These representations are derived through cascades of…

Sparse coding networks, which utilize unsupervised learning to maximize coding efficiency, have successfully reproduced response properties found in primary visual cortex \cite{AN:OlshausenField96}. However, conventional sparse coding…

Precortical neural systems encode information collected by the senses, but the driving principles of the encoding used have remained a subject of debate. We present a model of retinal coding that is based on three constraints: information…

Sparse coding algorithms trained on natural images can accurately predict the features that excite visual cortical neurons, but it is not known whether such codes can be learned using biologically realistic plasticity rules. We have…

Recognition of speech, and in particular the ability to generalize and learn from small sets of labelled examples like humans do, depends on an appropriate representation of the acoustic input. We formulate the problem of finding robust…

Neurons in the main center of convergence in the auditory midbrain, the central nucleus of the inferior colliculus (ICC) have been shown to display either linear significant receptive fields, or both, linear and nonlinear significant…

Self-supervised speech representations are known to encode both speaker and phonetic information, but how they are distributed in the high-dimensional space remains largely unexplored. We hypothesize that they are encoded in orthogonal…

Speaker identity plays a significant role in human communication and is being increasingly used in societal applications, many through advances in machine learning. Speaker identity perception is an essential cognitive phenomenon that can…

Linear Non-Linear(LN) models are widely used to characterize the receptive fields of early-stage auditory processing. We apply the principle of efficient coding to the LN model of Spectro-Temporal Receptive Fields(STRFs) of the neurons in…

Typically, unsupervised segmentation of speech into the phone and word-like units are treated as separate tasks and are often done via different methods which do not fully leverage the inter-dependence of the two tasks. Here, we unify them…

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…

This paper presents a theory by which idealized models of auditory receptive fields can be derived in a principled axiomatic manner, from a set of structural properties to enable invariance of receptive field responses under natural sound…

The advent of neural audio codecs has increased in popularity due to their potential for efficiently modeling audio with transformers. Such advanced codecs represent audio from a highly continuous waveform to low-sampled discrete units. In…

Classical auditory-periphery models, exemplified by Bruce et al., 2018, provide high-fidelity simulations but are stochastic and computationally demanding, limiting large-scale experimentation and low-latency use. Prior neural encoders…

The speech signal conveys information on different time scales from short time scale or segmental, associated to phonological and phonetic information to long time scale or supra segmental, associated to syllabic and prosodic information.…

A computational theory for classification of natural biosonar targets is developed based on the properties of an example stimulus ensemble. An extensive set of echoes (84 800) from four different foliages was transcribed into a spike code…

We argue that training autoencoders to reconstruct inputs from noised versions of their encodings, when combined with perceptual losses, yields encodings that are structured according to a perceptual hierarchy. We demonstrate the emergence…

Spatio-temporal receptive field (STRF) models are frequently used to approximate the computation implemented by a sensory neuron. Typically, such STRFs are assumed to be smooth and sparse. Current state-of-the-art approaches for estimating…