Cross database audio visual speech adaptation for phonetic spoken term detection
We show that the use of visual information helps both phone recognition and spoken term detection accuracy.Fused HMM adaptation could be utilized to benefit from multiple databases when training audio visual phone modelsAn additional audio adaptation ...
Speech enhancement using sparse dictionary learning in wavelet packet transform domain
A new learning-based speech enhancement method via sparse representation in wavelet packet transform domain is presented.The dictionary learning procedure for training data of speech and noise signals based on coherence criterion are proposed.The ...
Regularization of neural network model with distance metric learning for i-vector based spoken language identification
Pair-wise distance metric learning was designed on the feature transform layers.Stacking a soft-max layer on the feature transform layers as a classifier layer.Learning the coupled functions in feature extraction and classification layers with a ...
Generalisation in named entity recognition
Quantitative study of NER performance in diverse corpora of different genres, including newswire and social media.Multiple state of the art NER approaches are tested.Possible reasons for NER failure are analysed and quantified: NE diversity, unseen NEs ...
