Search Results for author: Philip Woodland

Found 4 papers, 0 papers with code

Multi-Span Acoustic Modelling using Raw Waveform Signals

no code implementations21 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.

Acoustic Modelling Automatic Speech Recognition +1

Semi-tied Units for Efficient Gating in LSTM and Highway Networks

no code implementations18 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.

speech-recognition Speech Recognition

High Order Recurrent Neural Networks for Acoustic Modelling

no code implementations22 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.

Acoustic Modelling speech-recognition +1

Improved TDNNs using Deep Kernels and Frequency Dependent Grid-RNNs

no code implementations18 Feb 2018 Florian Kreyssig, Chao Zhang, Philip Woodland

Time delay neural networks (TDNNs) are an effective acoustic model for large vocabulary speech recognition.

speech-recognition Speech Recognition

Cannot find the paper you are looking for? You can Submit a new open access paper.