Time-frequency analysis: theory and applications
Time-frequency analysis: theory and applications
Learning Overcomplete Representations
Neural Computation
Natural Computing: an international journal
A New Denoising Approach for Sound Signals Based on Non-negative Sparse Coding of Power Spectra
ISNN '08 Proceedings of the 5th international symposium on Neural Networks: Advances in Neural Networks, Part II
Auditory sparse representation for robust speaker recognition based on tensor structure
EURASIP Journal on Audio, Speech, and Music Processing - Intelligent Audio, Speech, and Music Processing Applications
Auditory cortical representations of speech signals for phoneme classification
MICAI'07 Proceedings of the artificial intelligence 6th Mexican international conference on Advances in artificial intelligence
ICANN'07 Proceedings of the 17th international conference on Artificial neural networks
A hierarchical framework for spectro-temporal feature extraction
Speech Communication
Bioinspired sparse spectro-temporal representation of speech for robust classification
Computer Speech and Language
Hi-index | 0.00 |
Recent studies of biological auditory processing have revealed that sophisticated spectrotemporal analyses are performed by central auditory systems of various animals. The analysis is typically well matched with the statistics of relevant natural sounds, suggesting that it produces an optimal representation of the animal's acoustic biotope. We address this topic using simulated neurons that learn an optimal representation of a speech corpus. As input, the neurons receive a spectrographic representation of sound produced by a peripheral auditory model. The output representation is deemed optimal when the responses of the neurons are maximally sparse. Following optimization, the simulated neurons are similar to real neurons in many respects. Most notably, a given neuron only analyzes the input over a localized region of time and frequency. In addition, multiple subregions either excite or inhibit the neuron, together producing selectivity to spectral and temporal modulation patterns. This suggests that the brain's solution is particularly well suited for coding natural sound; therefore, it may prove useful in the design of new computational methods for processing speech.