Hierarchical spike coding of sound
We develop a probabilistic generative model for representing acoustic event structure at multiple scales via a two-stage hierarchy. The first stage consists of a spiking representation which encodes a sound with a sparse set of kernels at different frequencies positioned precisely in time. The coarse time and frequency statistical structure of the first-stage spikes is encoded by a second stage spiking representation, while fine-scale statistical regularities are encoded by recurrent interactions within the first-stage. When fitted to speech data, the model encodes acoustic features such as harmonic stacks, sweeps, and frequency modulations, that can be composed to represent complex acoustic events. The model is also able to synthesize sounds from the higher-level representation and provides significant improvement over wavelet thresholding techniques on a denoising task.
Code (0)
등록된 구현이 없습니다.
Tasks
DenoisingSimilar Papers 제목 키워드 기반
Robust Environmental Sound Recognition with Sparse Key-point Encoding and Efficient Multi-spike Learning
The capability for environmental sound recognition (ESR) can determine the fitness of individuals in a way to avoid dangers or pursue opportunities when critical sound events occur. It still remains mysterious about the …
Decision MakingA General-Purpose Neuromorphic Sensor based on Spiketrum Algorithm: Hardware Details and Real-life Applications
Spiking Neural Networks (SNNs) offer a biologically inspired computational paradigm, enabling energy-efficient data processing through spike-based information transmission. Despite notable advancements in hardware for SN…
ECG ClassificationSpiketrum: An FPGA-based Implementation of a Neuromorphic Cochlea
This paper presents a novel FPGA-based neuromorphic cochlea, leveraging the general-purpose spike-coding algorithm, Spiketrum. The focus of this study is on the development and characterization of this cochlea model, whi…
Cochlear detection of double-slip motion in cello bowing
A double-slip motion of a cello sound is investigated experimentally with a bowing machine and analyzed using a Finite-Difference Time Domain (FDTD) cochlear model. A double-slip sound is investigated. Here the sawtooth …
Unsupervised Regenerative Learning of Hierarchical Features in Spiking Deep Networks for Object Recognition
We present a spike-based unsupervised regenerative learning scheme to train Spiking Deep Networks (SpikeCNN) for object recognition problems using biologically realistic leaky integrate-and-fire neurons. The training met…
DecoderGeneral ClassificationObject Recognition