In this paper, we cast discriminative training problems into standard linear programming (LP) optimization. Besides being convex and having globally optimal solution(s), LP progra...
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...
Multilingual speech recognition obviously involves numerous research challenges, including common phoneme sets, adaptation on limited amount of training data, as well as mixed lan...
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...
Spoken language is one of the most intuitive forms of interaction between humans and agents. Unfortunately, agents that interact with people using natural language often experienc...