Speech Prediction using an Adaptive Recurrent Neural Network with Application to Packet Loss Concealment

Abstract

This paper proposes a novel approach for speech signal prediction based on a recurrent neural network (RNN). Unlike existing RNN-based predictors, which operate on parametric features and are trained offline on a large collection of such features, the proposed predictor operates directly on speech samples and is trained online on the recent past of the speech signal. Optionally, the network can be pre-trained offline to speed-up convergence at start-up. The proposed predictor is a single end-to-end network that captures all sorts of dependencies between samples, and therefore has the potential to outperform classical linear/non-linear and short-term/long-term speech predictor structures. We apply it to the packet loss concealment (PLC) problem and show that it outperforms the standard ITU G.711 Appendix I PLC technique.

References in corpus (1)

• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation

Cited by in corpus (4)

• ConcealNet: An End-to-end Neural Network for Packet Loss Concealment in Deep Speech Emotion Recognition
• On Deep Speech Packet Loss Concealment: A Mini-Survey
• "I have vxxx bxx connexxxn!": Facing Packet Loss in Deep Speech Emotion Recognition
• Simultaneous Denoising and Localization Network for Photoacoustic Target Localization