Design, development and field evaluation of a Spanish into sign language translation system

This paper describes the design, development and field evaluation of a machine translation system from Spanish to Spanish Sign Language (LSE: Lengua de Signos Española). The developed system focuses on helping Deaf people when they want to renew their Driver’s License. The system is made up of a speech recognizer (for decoding the spoken utterance into a word sequence), a natural language translator (for converting a word sequence into a sequence of signs belonging to the sign language), and a 3D avatar animation module (for playing back the signs). For the natural language translator, three technological approaches have been implemented and evaluated: an example-based strategy, a rule-based translation method and a statistical translator. For the final version, the implemented language translator combines all the alternatives into a hierarchical structure. This paper includes a detailed description of the field evaluation. This evaluation was carried out in the Local Traffic Office in Toledo involving real government employees and Deaf people. The evaluation includes objective measurements from the system and subjective information from questionnaires. The paper details the main problems found and a discussion on how to solve them (some of them specific for LSE).

Relevance of the glottal pulse and the vocal tract in gender detection

Gender detection is a very important objective to improve efficiency in tasks as speech or speaker recognition, among others. Traditionally gender detection has been focused on fundamental frequency (f0) and cepstral features derived from voiced segments of speech. The methodology presented here consists in obtaining uncorrelated glottal and vocal tract components which are parameterized as mel-frequency coefficients. K-fold and cross-validation using QDA and GMM classifiers showed that better detection rates are reached when glottal source and vocal tract parameters are used in a gender-balanced database of running speech from 340 speakers.

Comparison of starts and turns of national and regional level swimmers by individualized-distance measurements

The aim of this study was to compare the race characteristics of the start and turn segments of national and regional level swimmers. In the study, 100 and 200-m events were analysed during the finals session of the Open Comunidad de Madrid (Spain) tournament. The “individualized-distance” method with two-dimensional direct linear transformation algorithm was used to perform race analyses. National level swimmers obtained faster velocities in all race segments and stroke comparisons,although significant inter-level differences in start velocity were only obtained in half (8 out of 16) of the analysed events. Higher level swimmers also travelled for longer start and turn distances but only in the race segments where the gain of speed was high. This was observed in the turn segments, in the backstroke and butterfly strokes and during the 200-m breaststroke event, but not in any of the freestyle events. Time improvements due to the appropriate extension of the underwater subsections appeared to be critical for the end race result and should be carefully evaluated by the “individualized-distance” method.

Evaluating a Speech Communication System for deaf people

This paper describes the development of an Advanced Speech Communication System for Deaf People and its field evaluation in a real application domain: the renewal of Driver’s License. The system is composed of two modules. The first one is a Spanish into Spanish Sign Language (LSE: Lengua de Signos Española) translation module made up of a speech recognizer, a natural language translator (for converting a word sequence into a sequence of signs), and a 3D avatar animation module (for playing back the signs). The second module is a Spoken Spanish generator from sign-writing composed of a visual interface (for specifying a sequence of signs), a language translator (for generating the sequence of words in Spanish), and finally, a text to speech converter. For language translation, the system integrates three technologies: an example-based strategy, a rule-based translation method and a statistical translator. This paper also includes a detailed description of the evaluation carried out in the Local Traffic Office in the city of Toledo (Spain) involving real government employees and deaf people. This evaluation includes objective measurements from the system and subjective information from questionnaires. Finally, the paper reports an analysis of the main problems and a discussion about possible solutions.

Caracterización multiescala de objetos como herramienta para la clasificación de imágenes de alta resolución espacial

This paper presents a new methodology, simple and affordable, for the definition and characterization of objects at different scales in high spatial resolution images. The objects have been generated by integrating texturally and spectrally homogeneous segments. The former have been obtained from the segmentation of Wavelet coefficients of the panchromatic image. The multi-scale character of this transform has yielded texturally homogeneous segments of different sizes for each of the scales. The spectrally homogeneous segments have been obtained by segmenting the classified corresponding multispectral image. In this way, it has been defined a set of objects characterized by different attributes, which give to the objects a semantic meaning, allowing to determine the similarities and differences between them. To demonstrate the capabilities of the methodology proposed, different experiments of unsupervised classification of a Quickbird image have been carried out, using different subsets of attributes and 1-D ascendant hierarchical classifier. Obtained results have shown the capability of the proposed methodology for separating semantic objects at different scales, as well as, its advantages against pixel-based image interpretation.