An RNN-Based Speech-Music Discrimination Used for Hybrid Audio Coder.

Wanzhao Yang Weiping Tu Jiaxi Zheng Xiong Zhang Yuhong Yang Yucheng Song

Published in: MMM (1) (2018)

Keyphrases

speech music discrimination
gaussian mixture model
recurrent neural networks
nearest neighbor
speech corpus
image compression
subband
unsupervised learning
image segmentation
pattern recognition
feature vectors
image coding
bitstream
compression ratio
image coder