Learn More
In the framework of the DIHANA project, we present the acquisition process of a spontaneous speech dialogue corpus in Spanish. The selected application consists of information retrieval by telephone for nationwide trains. A total of 900 dialogues from 225 users were acquired using the Wizard of Oz technique. In this work, we present the design and planning(More)
In this work, we propose and compare two different approaches to a two-level language model. Both of them are based on phrase classes but they consider different ways of dealing with phrases into the classes. We provide a complete formulation consistent with the two approaches. The language models proposed were integrated into an Automatic Speech(More)
In this paper, a task of human-machine interaction based on speech is presented. The specific task consists on the use and control of a set of home appliances through a turn-based dialogue system. This work focuses on the first part of the dialogue system, the Automatic Speech Recognition (ASR) system. Two lines of work are taken into account to improve the(More)
Articulatory information has demonstrated to be useful to improve phone recognition performance in ASR systems, being the use of Neural Networks the most successful method to detect articulatory gestures from the speech signal. On the other hand, Stochastic Finite State Automata (SFSA) have been effectively used in many speech-input natural language tasks.(More)