Nonlinear Prediction of Speech by Echo State Networks

Ziyue Zhao, Huijun Liu, Tim Fingscheidt

Abstract

Speech prediction plays a key role in many speech signal processing and speech communication methods. While linear prediction of speech is well-studied, nonlinear speech prediction increasingly receives interest especially with the vast amount of new neural network topologies proposed recently. In this paper, nonlinear speech prediction is conducted by a special kind of recurrent neural network not requiring any training beforehand, the echo state network, which adaptively updates its output layer weights. Simulations show its superior performance compared to other well-known prediction approaches in terms of the prediction gain, exceeding all baselines in all conditions by up to 8 dB.
BibTeX
@inproceedings{zhao2018nonlinear,
  author = {Ziyue Zhao and Huijun Liu and Tim Fingscheidt},
  title = {{Nonlinear Prediction of Speech by Echo State Networks}},
  booktitle = {EUSIPCO},
  year = {2018},
  doi = {10.23919/eusipco.2018.8553190},
}

Loading related content...

Figure