Threshold Filtering for Phoneme Pronunciation Signals Based on FrFT.

Zhenyan Fan Jun Yu Zhongxiao Li Xiaodong Zhuang Nikos E. Mastorakis

Published in: EECS (2018)

Keyphrases

fractional fourier transform
speech recognition
log polar
automatic speech recognition
hidden markov models
language model
signal processing
speaker independent
computer vision
template matching
object recognition
natural images
image patches
spatial domain
fourth order
automatic speech recognition systems