We propose novel approaches for optimizing the detection performance in spoken language recognition. Two objective functions are designed to directly relate model parameters to tw...
One commonly used approach for language recognition is to convert the input speech into a sequence of tokens such as words or phones and then to use these token sequences to deter...
Many recent advances in complex domains such as Natural Language Processing (NLP) have taken a discriminative approach in conjunction with the global application of structural and...
We propose a simple generative, syntactic language model that conditions on overlapping windows of tree context (or treelets) in the same way that n-gram language models condition...
Discriminative methods have shown significant improvements over traditional generative methods in many machine learning applications, but there has been difficulty in extending th...