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.

Quantitative evaluation of artifact removal in real magnetoencephalogram signals with blind source separation

The magnetoencephalogram (MEG) is contaminated with undesired signals, which are called artifacts. Some of the most important ones are the cardiac and the ocular artifacts (CA and OA, respectively), and the power line noise (PLN). Blind source separation (BSS) has been used to reduce the influence of the artifacts in the data. There is a plethora of BSS-based artifact removal approaches, but few comparative analyses. In this study, MEG background activity from 26 subjects was processed with five widespread BSS (AMUSE, SOBI, JADE, extended Infomax, and FastICA) and one constrained BSS (cBSS) techniques. Then, the ability of several combinations of BSS algorithm, epoch length, and artifact detection metric to automatically reduce the CA, OA, and PLN were quantified with objective criteria. The results pinpointed to cBSS as a very suitable approach to remove the CA. Additionally, a combination of AMUSE or SOBI and artifact detection metrics based on entropy or power criteria decreased the OA. Finally, the PLN was reduced by means of a spectral metric. These findings confirm the utility of BSS to help in the artifact removal for MEG background activity.

Blind reconiliation

Information reconciliation is a crucial procedure in the classical post-processing of quantum key distribution (QKD). Poor reconciliation e?ciency, revealing more information than strictly needed, may compromise the maximum attainable distance, while poor performance of the algorithm limits the practical throughput in a QKD device. Historically, reconciliation has been mainly done using close to minimal information disclosure but heavily interactive procedures, like Cascade, or using less e?cient but also less interactive ?just one message is exchanged? procedures, like the ones based in low-density parity-check (LDPC) codes. The price to pay in the LDPC case is that good e?ciency is only attained for very long codes and in a very narrow range centered around the quantum bit error rate (QBER) that the code was designed to reconcile, thus forcing to have several codes if a broad range of QBER needs to be catered for. Real world implementations of these methods are thus very demanding, either on computational or communication resources or both, to the extent that the last generation of GHz clocked QKD systems are ?nding a bottleneck in the classical part. In order to produce compact, high performance and reliable QKD systems it would be highly desirable to remove these problems. Here we analyse the use of short-length LDPC codes in the information reconciliation context using a low interactivity, blind, protocol that avoids an a priori error rate estimation. We demonstrate that 2×103 bits length LDPC codes are suitable for blind reconciliation. Such codes are of high interest in practice, since they can be used for hardware implementations with very high throughput.

Simultaneously measuring two ultrashort laser pulses on a single-shot using double-blind frequency-resolved optical gating

We demonstrate a simple self-referenced single-shot method for simultaneously measuring two different arbitrary pulses, which can potentially be complex and also have very different wavelengths. The method is a variation of cross-correlation frequency-resolved optical gating (XFROG) that we call double-blind (DB) FROG. It involves measuring two spectrograms, both of which are obtained simultaneously in a single apparatus. DB FROG retrieves both pulses robustly by using the standard XFROG algorithm, implemented alternately on each of the traces, taking one pulse to be ?known? and solving for the other. We show both numerically and experimentally that DB FROG using a polarization-gating beam geometry works reliably and appears to have no nontrivial ambiguities.

Novel fast random search clustering approach for mixing matrix identification in MIMO linear blind inverse problems with sparse inputs

In this paper we propose a novel fast random search clustering (RSC) algorithm for mixing matrix identification in multiple input multiple output (MIMO) linear blind inverse problems with sparse inputs. The proposed approach is based on the clustering of the observations around the directions given by the columns of the mixing matrix that occurs typically for sparse inputs. Exploiting this fact, the RSC algorithm proceeds by parameterizing the mixing matrix using hyperspherical coordinates, randomly selecting candidate basis vectors (i.e. clustering directions) from the observations, and accepting or rejecting them according to a binary hypothesis test based on the Neyman–Pearson criterion. The RSC algorithm is not tailored to any specific distribution for the sources, can deal with an arbitrary number of inputs and outputs (thus solving the difficult under-determined problem), and is applicable to both instantaneous and convolutive mixtures. Extensive simulations for synthetic and real data with different number of inputs and outputs, data size, sparsity factors of the inputs and signal to noise ratios confirm the good performance of the proposed approach under moderate/high signal to noise ratios. RESUMEN. Método de separación ciega de fuentes para señales dispersas basado en la identificación de la matriz de mezcla mediante técnicas de "clustering" aleatorio.

Developing an information system for deaf

This paper presents the SAILSE Project (Sistema Avanzado de Información en Lengua de Signos Española ? Spanish Sign Language Advanced Information System). This project aims to develop an interactive system for facilitating the communication between a hearing and a deaf person. The first step has been the linguistic study, including a sentence collection, its translation into LSE (Lengua de Signos Española - Spanish Sign Language), and sign generation. After this analysis, the paper describes the interactive system that integrates an avatar to represent the signs, a text to speech converter and several translation technologies. Finally, this paper presents the set up carried out with deaf people and the main conclusions extracted from it.

Translating bus information into sign language for deaf people

This paper describes the application of language translation technologies for generating bus information in Spanish Sign Language (LSE: Lengua de Signos Española). In this work, two main systems have been developed: the first for translating text messages from information panels and the second for translating spoken Spanish into natural conversations at the information point of the bus company. Both systems are made up of a natural language translator (for converting a word sentence into a sequence of LSE signs), and a 3D avatar animation module (for playing back the signs). For the natural language translator, two technological approaches have been analyzed and integrated: an example-based strategy and a statistical translator. When translating spoken utterances, it is also necessary to incorporate a speech recognizer for decoding the spoken utterance into a word sequence, prior to the language translation module. This paper includes a detailed description of the field evaluation carried out in this domain. This evaluation has been carried out at the customer information office in Madrid involving both real bus company employees and deaf people. The evaluation includes objective measurements from the system and information from questionnaires. In the field evaluation, the whole translation presents an SER (Sign Error Rate) of less than 10% and a BLEU greater than 90%.

Methodology for developing an advanced communications system for the Deaf in a new domain

A methodology for developing an advanced communications system for the Deaf in a new domain is presented in this paper. This methodology is a user-centred design approach consisting of four main steps: requirement analysis, parallel corpus generation, technology adaptation to the new domain, and finally, system evaluation. During the requirement analysis, both the user and technical requirements are evaluated and defined. For generating the parallel corpus, it is necessary to collect Spanish sentences in the new domain and translate them into LSE (Lengua de Signos Española: Spanish Sign Language). LSE is represented by glosses and using video recordings. This corpus is used for training the two main modules of the advanced communications system to the new domain: the spoken Spanish into the LSE translation module and the Spanish generation from the LSE module. The main aspects to be generated are the vocabularies for both languages (Spanish words and signs), and the knowledge for translating in both directions. Finally, the field evaluation is carried out with deaf people using the advanced communications system to interact with hearing people in several scenarios. In this evaluation, the paper proposes several objective and subjective measurements for evaluating the performance. In this paper, the new considered domain is about dialogues in a hotel reception. Using this methodology, the system was developed in several months, obtaining very good performance: good translation rates (10% Sign Error Rate) with small processing times, allowing face-to-face dialogues.