Ciro Gracia

The e-Sentencias Prototype: A Procedural Ontology for Legal Multimedia Applications in the Spanish Civil Courts

Search, retrieval, and management of multimedia contents are challenging tasks for users and researchers alike. We introduce a software-hardware system for the global management of the multimedia contents produced by Spanish Civil Courts. The ultimate goal is to obtain an automatic classification of images and segments of the audiovisual records that, coupled with textual semantics, allows an efficient navigation and retrieval of judicial documents and additional legal sources. This paper describes our knowledge acquisition process, sets a typology of Spanish Civil hearings as performed in practice, and a preliminary procedural ontology at its actual stage of development (e-Sentencias ontology). A discussion on procedural, contextual and multimedia ontologies is also provided.

Phoneme-Lattice to Phoneme-Sequence Matching Algorithm Based on Dynamic Programming

A novel phoneme-lattice to phoneme-sequence matching algorithm based on dynamic programming is presented in this paper. Phoneme lattices have been shown to be a good choice to encode in a compact way alternative decoding hypotheses from a speech recognition system. These are typically used for the spoken term detection and keyword-spotting tasks, where a phoneme sequence query is matched to a reference lattice. Most current approaches suffer from a lack of flexibility whenever a match allowing phoneme insertions, deletions and substitutions is to be found. We introduce a matching approach based on dynamic programming, originally proposed for Minimum Bayes decoding on speech recognition systems. The original algorithm is extended in several ways. First, a self-trained phoneme confusion matrix for phoneme comparison is applied as phoneme penalties. Also, posterior probabilities are computed per arc, instead of likelihoods and an acoustic matching distance is combined with the edit distance at every arc. Finally, total matching scores are normalized based on the length of the optimum alignment path. The resulting algorithm is compared to a state-of-the-art phoneme-lattice-to-string matching algorithm showing relative precision improvements over 20% relative on an isolated word retrieval task.