no code implementations • 21 Jun 2019 • Patrick von Platen, Chao Zhang, Philip Woodland
This paper proposes a novel multi-span structure for acoustic modelling based on the raw waveform with multiple streams of CNN input layers, each processing a different span of the raw waveform signal.
no code implementations • 18 Jun 2018 • Chao Zhang, Philip Woodland
Gating is a key technique used for integrating information from multiple sources by long short-term memory (LSTM) models and has recently also been applied to other models such as the highway network.
no code implementations • 22 Feb 2018 • Chao Zhang, Philip Woodland
Vanishing long-term gradients are a major issue in training standard recurrent neural networks (RNNs), which can be alleviated by long short-term memory (LSTM) models with memory cells.
no code implementations • 18 Feb 2018 • Florian Kreyssig, Chao Zhang, Philip Woodland
Time delay neural networks (TDNNs) are an effective acoustic model for large vocabulary speech recognition.