Language models for speech recognition tend to be brittle across domains, since their performance is vulnerable to changes in the genre or topic of the text on which they are trai...
The vocabulary used in speech usually consists of two types of words: a limited set of common words, shared across multiple documents, and a virtually unlimited set of rare words, ...
Stefan Kombrink, Mirko Hannemann, Lukas Burget, Hy...
This paper describes a new toolkit - SCARF - for doing speech recognition with segmental conditional random fields. It is designed to allow for the integration of numerous, possib...
A new language model for speech recognition inspired by linguistic analysis is presented. The model develops hidden hierarchical structure incrementally and uses it to extract mea...
Although speech, derived from reading texts, and similar types of speech, e.g. that from reading newspapers or that from news broadcast, can be recognized with high accuracy, recog...