Efficient auditory coding

By Evan C. Smith, Michael S. Lewicki. 2006

639 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Signal Processing

Citations in the corpus

Learning Filterbanks from Raw Speech for Phone Recognition (2017, background): “This is a type of asymmetry also found in human and animal auditory filters estimated from behavioral and physiological data [24].”
ABX-Discriminability Measures and Applications. (Mesures de discriminabilité ABX et applications) (2016, result): “Second, in a famous computational study, Lewicki [153] obtained very similar results when optimizing a filterbank for sparse decomposition of either natural sounds or speech sounds.”
Compressed-Domain Ship Detection on Spaceborne Optical Image Using Deep Neural Network and Extreme Learning Machine (2015, background): “wavelet features, feature detectors localized in both time and frequency domains can be obtained [19], [20].”
Learning emotion-based acoustic features with deep belief networks (2011, background): “Sparse representations are particularly desirable in the application of feature learning for forming compact representations of high-dimensional spectral data, and previous work in sparse methods has also shown that such representations lead to basis functions that closely model mammalian auditory f”
An Intelligent Fault Diagnosis Method Using Unsupervised Feature Learning Towards Mechanical Big Data (2016, methodology): “Therefore, we fit each weight vectors using Gabor function f(d) [46], [47]”
Unsupervised Filterbank Learning Using Convolutional Restricted Boltzmann Machine for Environmental Sound Classification (2017, background): “The work of [26, 27] analyze the filterbank on separate database of animal vocalizations and environmental sounds.”
Unsupervised feature learning for audio classification using convolutional deep belief networks (2009, background): “Previous work [1, 2] revealed that learning a sparse representation of auditory signals leads to filters that closely correspond to those of neurons in early audio processing in mammals.”
On the information rate of speech communication (2017, background): “The fact that (6) gives a low bottleneck supports the results of [17], which suggested that the acoustic structure of speech might be adapted to the coding capability of the mammalian auditory system.”
Bayesian reasoning and machine learning (2012, neutral): “Such sparse-representations are common in theoretical neurobiology where issues of energy efficiency, rapidity of processing and robustness are of interest[214, 155, 252].”
Sparse Representation of Sounds in the Unanesthetized Auditory Cortex (2008, background): “A growing body of theoretical work on sparse representations suggest they may be useful for computation (Olshausen and Field, 1997; Lewicki, 2002; Olshausen and Field, 2004; Guyonneau et al., 2004; Smith and Lewicki, 2006; Asari et al., 2006).”