In the context of spoken language interpretation, this paper introduces a stochastic approach to infer and compose semantic structures. Semantic frame structures are directly deri...
The parallel phone recognition followed by language model (PPRLM) architecture represents one of the state-of-the-art spoken language identification systems. A PPRLM system compris...
When building a new spoken dialogue application, large amounts of domain specific data are required. This paper addresses the issue of generating in-domain training data when litt...
This paper studies the impact of written language variations and the way it affects the capitalization task over time. A discriminative approach, based on maximum entropy models, ...
Spoken Document Retrieval (SDR) is a promising technology for enhancing the utility of spoken materials. After the spoken documents have been transcribed by using a Large Vocabula...