We propose a Minimum Verification Error (MVE) training scenario to design and adapt an HMM-based speaker verification system. By using the discriminative training paradigm, we show that customer and background models can be jointly estimated so that the expected number of verification errors (false accept and false reject) on the training corpus are minimized. An experimental evaluation of a fixed password speaker verification task over the telephone network was carried out. The evaluation shows that MVE training/adaptation performs as well as MLE training and MAP adaptation when performance is measured by average individual equal error rate (based on a posteriori threshold assignment). After model adaptation, both approaches lead to an individual equal error-rate close to 0.6%. However, experiments performed with a priori dynamic threshold assignment show that MVE adapted models exhibit false rejection and false acceptance rates 45% lower than the MAP adapted models, and therefore lead to the design of a more robust system for practical applications.

In this paper we explore the use of features derived from multiresolution analysis of speech and the Teager Energy Operator for classification of drivers' speech under stressed conditions. The potential stress categories are determined by driving speed and the frequency with which the driver has to solve a mental task while driving. We first use an unsupervised approach to gain some understanding as to whether the discrete stress categories form meaningful clusters in feature space, and use the clustering results to build a user-dependent recognition system which combines local discriminants of 4 discreet stress categories. Recognition results are reported for 4 subjects. 1 Introduction Much of the current effort on studying speech under stress has been aimed at detecting several stress conditions for improving the robustness of speech recognizers; typical categories of speech under stress have targeted perceptual (e.g. Lombard effect), psychological (e.g. timed tasks), as well as ph...

This paper deals with the probabilistic modeling of an environment that a robot has to navigate in. We use a method for the probabilistic modeling of space called the Bayesian Map formalism. This formalism allows incremental building of models: we define the Superposition operator, which is a formally well-defined operator. We present first a syntactic version of this operator, and second, a version where the previously obtained model is refined and enriched by experimental learning. In the resulting superposed map, locations are the conjunction of underlying possible locations, which allows for more precise localization and more complex tasks. A theoretical example validates the concept, and hints at its usefulness for realistic robotic scenarios.

Abstract — This paper deals with the probabilistic modeling of space, in the context of mobile robot navigation. We define a formalism called the Bayesian Map, which allows incremental building of models, thanks to the Superposition operator, which is a formally well-defined operator. Firstly, we present a syntactic version of this operator, and secondly, a version where the previously obtained model is enriched by experimental learning. In the resulting map, locations are the conjunction of underlying possible locations, which allows for more precise localization and more complex tasks. A theoretical example validates the concept, and hints at its usefulness for realistic robotic scenarios. I. INTRODUCTION AND RELATED WORK In the domain of mobile robotics, modeling the environment that a robot has to face is a crucial problem. Whether it is a robotic personal assistant operating indoors (e.g. in a hospital,

One popular form of semantic search observed in several modern search engines is to recognize query patterns that trigger instant answers or domain-specific search, producing semantically enriched search results. This often requires understanding the query intent in addition to the meaning of the query terms in order to access structured data sources. A major challenge in intent understanding is to construct a domain-dependent schema and to annotate search queries based on such a schema, a process that to date has required much manual annotation effort. We present an unsupervised method for clustering queries with similar intent and for producing a pattern consisting of a sequence of semantic concepts and/or lexical items for each intent. Furthermore, we leverage the discovered intent patterns to automatically annotate a large number of queries beyond those used in clustering. We evaluated our method on 10 selected domains, discovering over 1400 intent patterns and automatically annotating 125K (and potentially many more) queries. We found that over 90 % of patterns and 80 % of instance annotations tested are judged to be correct by a majority of annotators.