A common way to represent a time series is to divide it into shortduration blocks, each of which is then represented by a set of basis functions. A limitation of this approach, ho...
This paper presents work done at Cambridge University, on the TREC7 Spoken Document Retrieval (SDR) Track. The broadcast news audio was transcribed using a 2-pass gender-dependent...
Sue E. Johnson, P. Jourlin, G. L. Moore, Karen Spa...
Abstract. Developers express the meaning of the domain ideas in specifically selected identifiers and comments that form the target implemented code. Software maintenance requires ...
This paper presents trainable methods for generating letter to sound rules from a given lexicon for use in pronouncing out-ofvocabulary words and as a method for lexicon compressi...
We introduce, analyze and demonstrate a recursive hierarchical generalization of the widely used hidden Markov models, which we name Hierarchical Hidden Markov Models (HHMM). Our m...