Improved neural network based language modelling and adaptation

12 years 11 months ago

Download mi.eng.cam.ac.uk

Neural network language models (NNLM) have become an increasingly popular choice for large vocabulary continuous speech recognition (LVCSR) tasks, due to their inherent generalisation and discriminative power. This paper present two techniques to improve performance of standard NNLMs. First, the

Junho Park, Xunying Liu, Mark J. F. Gales, Philip

Real-time Traffic

Inherent Generalisation | INTERSPEECH 2010 | Neural Network Language | Signal Processing | Vocabulary Continuous Speech |

claim paper

» Adaptive Wavelet Neural Network for Prediction of Hourly NOx and NO2 Concentrations

» Adaptive Importance Sampling to Accelerate Training of a Neural Probabilistic Language Mod...

» Neural Network Supported Adaptation in Casebased Reasoning

» Hierarchical Text Categorization Using Neural Networks

» Connectionist Models for Formal Knowledge Adaptation

» Oscillatory neural network for adaptive dynamical image processing

» Structured Output Layer neural network language model

» Traffic Prediction Based on Improved Neural Network

Post Info
More Details (n/a)

Added	18 May 2011
Updated	18 May 2011
Type	Journal
Year	2010
Where	INTERSPEECH
Authors	Junho Park, Xunying Liu, Mark J. F. Gales, Philip C. Woodland

Comments (0)

Sciweavers

Improved neural network based language modelling and adaptation

Inherent Generalisation | INTERSPEECH 2010 | Neural Network Language | Signal Processing | Vocabulary Continuous Speech |

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers