Marie-José Caraty

Learn More
In this paper, we compare three speaker recognition systems results (i.e. GMM, AHSM, ARVM) on the TIMIT and NTIMIT databases. In order to improve the results on the NTIMIT database, we present two more sophisticated systems: the first one is based on ARMAVector model, the second one is based on the utilisation of several AR-Vector models per speaker. We(More)
In this paper, we study various technics to improve the performance, to reduce the computation cost and the required memory of a recognition system based on HMM. For the efficiency of the system, we first study the optimization of the number of HMM parameters according to training data. We experiment a temporal control of the phonetic transitions on lexical(More)
The delta coefficients are a conventional method to include temporal information in the speech recognition systems. In particular, they are widely used in the gaussian HMM-based systems. Some attempts were made to introduce the delta coefficients in the K-Nearest Neighbours (K-NN) HMMbased system that we recently developed. An introduction of the delta(More)
The article describes the system we submitted for the three sub-challenges of INTERSPEECH 2012 Speaker Trait Challenge for the classification of the five personality traits of OCEAN, likability and intelligibility. The system was based on a two-class SVM-classifier using leave-one-speaker-out cross-validation to optimize SVM complexity parameter and to(More)
This article describes the two systems which we submitted for the Intoxication Sub-Challenge of INTERSPEECH 2011 Speaker State Challenge. At first, we developed an Extended Baseline System with a significant improvement of the unweighted accuracy compared to the Official Baseline System (OBS) on the development set. Then, we investigated the phonetic(More)
Most speaker-independent acoustic-phonetic decoding systems are based on hidden Markov models. Such systems lack a real temporal control for the phonetic models. Furthermore, inter-speaker variability makes speaker adaptation necessary. In order to solve these problems, we introduce two original approaches. On the one hand, discontinuities detected with the(More)
We develop a cooperation and a competition of two different natures modelizations. The first one, the GMM [1], is a modelization of the parametrisation distribution of the speaker speech. The second, the ARVM [2, 3], is a modelization of the speaker speech spectral evolution. To allow cooperation and competition between different modelizations we use a(More)