Dominique Massonié

Learn More
This paper presents the Speeral continuous speech recognition system developed in the LIA. Speeral uses a modified A* algorithm to find in the search graph the best path taking into account acoustic and linguistic constraints. Rather than words by words, the A* used in Speeral is based on a phoneme lattice previously generated. To avoid the backtraking(More)
In this paper a new computation and approximation scheme for Language Model Look-Ahead (LMLA) is introduced. The main benefit of LMLA is sharper pruning of the search space during the LVCSR decoding process. However LMLA comes with its own cost and is known to scale badly with both LM n-gram order and LM size. The proposed method tackles this problem with a(More)
This paper presents a system for large vocabulary continuous speech recognition in condition of constrained hardware resources. We investigate efficient pruning and caching strategy aiming to handle extensive acoustic and linguistic modeling. Software components are analyzed in terms of resource consuming. Then, we evaluate the system performance in extreme(More)
This paper deals with the difficult task of recognition of a large vocabulary of proper names in a directory assistance application. Research on the European project SMADA has shown that there is a need of an elaborate and effective decision strategy that limits the risk of false automation. This paper proposes a new strategy which integrates, as well as a(More)
In this paper we present an extension to our freely available modeling tool for specifying human-machine interfaces in automotive and non-automotive domains. The software tool has been extended to control and use a robot for speech synthesis, speech recognition and gestures. This enables linguists or human factors researchers to easily specify robot(More)
  • 1