Learning the Front-End Speech Feature with Raw Waveform for End-to-End Speaker Recognition.

Ningxin Liang Wei Xu Chengfang Luo Wenxiong Kang

Published in: ICCAI (2020)

Keyphrases

feature vectors
end to end
speaker recognition
gaussian mixture model
feature extraction
reinforcement learning
similarity measure
learning algorithm
image sequences
congestion control
neural network
wavelet transform
mixture model
key frames
speech signal
probabilistic neural network