Biologically-Inspired Spike-Based Automatic Speech Recognition of Isolated Digits Over a Reproducing Kernel Hilbert Space

Biologically-Inspired Spike-Based Automatic Speech Recognition of Isolated Digits Over a Reproducing Kernel Hilbert Space

This paper presents a novel real-time dynamic framework for quantifying time-series structure in spoken words using spikes. Audio signals are converted into multi-channel spike trains using a biologically-inspired leaky integrate-and-fire (LIF) spike generator. These spike trains are mapped into a f...

Full description

Bibliographic Details
Main Authors: Kan Li, José C. Príncipe
Format: Article
Language:English
Published: Frontiers Media S.A. 2018-04-01
Series:Frontiers in Neuroscience
Subjects:
spike-based learning
noise-robust automatic speech recognition (ASR)
keyword spotting
kernel adaptive filtering (KAF)
reproducing kernel Hilbert space (RKHS)
kernel method
Online Access:http://journal.frontiersin.org/article/10.3389/fnins.2018.00194/full

Internet

http://journal.frontiersin.org/article/10.3389/fnins.2018.00194/full

Similar Items