Wavelet-based cepstrum calculation

In this paper we present a new wavelet-based algorithm for low-cost computation of the cepstrum. It can be used for real time precise pitch determination in automatic speech and speaker recognition systems. Many wavelet families are examined to determine the one that works best. The results confirm the efficacy and accuracy of the proposed technique for pitch extraction. (C) 2008 Elsevier B.V. All rights reserved.

On the determination of epsilon during discriminative GMM training

Discriminative training of Gaussian Mixture Models (GMMs) for speech or speaker recognition purposes is usually based on the gradient descent method, in which the iteration step-size, ε, uses to be defined experimentally. In this letter, we derive an equation to adaptively determine ε, by showing that the second-order Newton-Raphson iterative method to find roots of equations is equivalent to the gradient descent algorithm. © 2010 IEEE.

Delimitação e alinhamento de conceitos lexicalizados no inglês norte-americano e no português brasileiro

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Schriftlicher Text im Film und seine Übersetzung : die Inserts der BBC-Serie Sherlock (2010-12) ; aus der Perspektive von Untertiteltheorie, Comictheorie und Translationspraxis

Die BBC-Serie SHERLOCK war 2011 eine der meistexportierten Fernsehproduktionen Großbritanniens und wurde weltweit in viele Sprachen übersetzt. Eine der Herausforderungen bei der Übersetzung stellen die Schrifteinblendungen der Serie (kurz: Inserts) dar. Die Inserts versprachlichen die Gedanken des Protagonisten, bilden schriftliche und digitale Kommunikation ab und zeichnen sich dabei durch ihre visuelle Auffälligkeit und teilweise als einzige Träger sprachlicher Kommunikation aus, womit sie zum wichtigen ästhetischen und narrativen Mittel in der Serie werden. Interessanterweise sind in der Übersetztung alle stilistischen Eigenschaften der Original-Inserts erhalten. In dieser Arbeit wird einerseits untersucht, wie Schrifteinblendungen im Film theoretisch beschrieben werden können, und andererseits, was sie in der Praxis so übersetzt werden können, wie es in der deutschen Version von Sherlock geschah. Zur theoretischen Beschreibung werden zunächst die Schrifteinblendungen in Sherlock Untertitelungsnormen anhand relevanter grundlegender semiotischer Dimensionen gegenübergestellt. Weiterhin wird das Verhältnis zwischen Schrifteinblendungen und Filmbild erkundet. Dazu wird geprüft, wie gut verschiedene Beschreibungsansätze zu Text-Bild-Verhältnissen aus der Sprachwissenschaft, Comicforschung, Übersetzungswissenschaft und Typografie die Einblendungen in Sherlock erklären können. Im praktischen Teil wird die Übersetzung der Einblendungen beleuchtet. Der Übersetzungsprozess bei der deutschen Version wird auf Grundlage eines Experteninterviews mit dem Synchronautor der Serie rekonstruiert, der auch für die Formulierung der Inserts zuständig war. Abschließend werden spezifische Übersetzungsprobleme der Inserts aus der zweiten Staffel von SHERLOCK diskutiert. Es zeigt sich, dass Untertitelungsnormen zur Beschreibung von Inserts nicht geeignet sind, da sie in Dimensionen wie Position, grafische Gestaltung, Animation, Soundeffekte, aber auch Timing stark eingeschränkt sind. Dies lässt sich durch das historisch geprägte Verständnis von Untertiteln erklären, die als möglichst wenig störendes Beiwerk zum fertigen Filmbild und -ablauf (notgedrungen) hinzugefügt werden, wohingegen für die Inserts in SHERLOCK teilweise sogar ein zentraler Platz in der Bild- und Szenenkomposition bereits bei den Dreharbeiten vorgesehen wurde. In Bezug auf Text-Bild-Verhältnisse zeigen sich die größten Parallelen zu Ansätzen aus der Comicforschung, da auch dort schriftliche Texte im Bild eingebettet sind anstatt andersherum. Allerdings sind auch diese Ansätze zur Beschreibung von Bewegung und Ton unzureichend. Die Erkundung der Erklärungsreichweite weiterer vielversprechender Konzepte, wie Interface und Usability, bleibt ein Ziel für künftige Studien. Aus dem Experteninterview lässt sich schließen, dass die Übersetzung von Inserts ein neues, noch unstandardisiertes Verfahren ist, in dem idiosynkratische praktische Lösungen zur sprachübergreifenden Kommunikation zwischen verschiedenen Prozessbeteiligten zum Einsatz kommen. Bei hochqualitative Produktionen zeigt ist auch für die ersetzende Insertübersetzung der Einsatz von Grafikern unerlässlich, zumindest für die Erstellung neuer Inserts als Übersetzungen von gefilmtem Text (Display). Hierbei sind die theoretisch möglichen Synergien zwischen Sprach- und Bildexperten noch nicht voll ausgeschöpft. Zudem zeigt sich Optimierungspotential mit Blick auf die Bereitstellung von sorgfältiger Dokumentation zur ausgangssprachlichen Version. Diese wäre als Referenzmaterial für die Übersetzung insbesondere auch für Zwecke der internationalen Qualitätssicherung relevant. Die übersetzten Inserts in der deutschen Version weisen insgesamt eine sehr hohe Qualität auf. Übersetzungsprobleme ergeben sich für das genretypische Element der Codes, die wegen ihrer Kompaktheit und multiplen Bezügen zum Film eine Herausforderung darstellen. Neben weiteren bekannten Übersetzungsproblemen wie intertextuellen Bezügen und Realia stellt sich immer wieder die Frage, wieviel der im Original dargestellten Insert- und Displaytexte übersetzt werden müssen. Aus Gründen der visuellen Konsistenz wurden neue Inserts zur Übersetzung von Displays notwendig. Außerdem stellt sich die Frage insbesondere bei Fülltexten. Sie dienen der Repräsentation von Text und der Erweiterung der Grenzen der fiktiv dargestellten Welt, sind allerdings mit hohem Übersetzungsaufwand bei minimaler Bedeutung für die Handlung verbunden.

Norms on the gender perception of role nouns in Czech, English, French, German, Italian, Norwegian, and Slovak

We collected norms on the gender stereotypicality of an extensive list of role nouns in Czech, English, French, German, Italian, Norwegian, and Slovak, to be used as a basis for the selection of stimulus materials in future studies. We present a Web-based tool (available at https://www.unifr.ch/lcg/) that we developed to collect these norms and that we expect to be useful for other researchers, as well. In essence, we provide (a) gender stereotypicality norms across a number of languages and (b) a tool to facilitate cross-language as well as cross-cultural comparisons when researchers are interested in the investigation of the impact of stereotypicality on the processing of role nouns.

Image Retrieval: The MIRACLE Approach

ImageCLEF is a pilot experiment run at CLEF 2003 for cross language image retrieval using textual captions related to image contents. In this paper, we describe the participation of the MIRACLE research team (Multilingual Information RetrievAl at CLEF), detailing the different experiments and discussing their preliminary results.

MIRACLE Approaches to Multilingual Information Retrieval: A Baseline for Future Research

This paper describes the first set of experiments defined by the MIRACLE (Multilingual Information RetrievAl for the CLEf campaign) research group for some of the cross language tasks defined by CLEF. These experiments combine different basic techniques, linguistic-oriented and statistic-oriented, to be applied to the indexing and retrieval processes.

GMM-based classifiers for the automatic detection of obstructive sleep apnea

The aim of automatic pathological voice detection systems is to serve as tools, to medical specialists, for a more objective, less invasive and improved diagnosis of diseases. In this respect, the gold standard for those system include the usage of a optimized representation of the spectral envelope, either based on cepstral coefficients from the mel-scaled Fourier spectral envelope (Mel-Frequency Cepstral Coefficients) or from an all-pole estimation (Linear Prediction Coding Cepstral Coefficients) forcharacterization, and Gaussian Mixture Models for posterior classification. However, the study of recently proposed GMM-based classifiers as well as Nuisance mitigation techniques, such as those employed in speaker recognition, has not been widely considered inpathology detection labours. The present work aims at testing whether or not the employment of such speaker recognition tools might contribute to improve system performance in pathology detection systems, specifically in the automatic detection of Obstructive Sleep Apnea. The testing procedure employs an Obstructive Sleep Apnea database, in conjunction with GMM-based classifiers looking for a better performance. The results show that an improved performance might be obtained by using such approach.

Desarrollo de una herramienta de análisis de la señal de voz

El habla es la principal herramienta de comunicación de la que dispone el ser humano que, no sólo le permite expresar su pensamiento y sus sentimientos sino que le distingue como individuo. El análisis de la señal de voz es fundamental para múltiples aplicaciones como pueden ser: síntesis y reconocimiento de habla, codificación, detección de patologías, identificación y reconocimiento de locutor… En el mercado se pueden encontrar herramientas comerciales o de libre distribución para realizar esta tarea. El objetivo de este Proyecto Fin de Grado es reunir varios algoritmos de análisis de la señal de voz en una única herramienta que se manejará a través de un entorno gráfico. Los algoritmos están siendo utilizados en el Grupo de investigación en Aplicaciones MultiMedia y Acústica de la Universidad Politécnica de Madrid para llevar a cabo su tarea investigadora y para ofertar talleres formativos a los alumnos de grado de la Escuela Técnica Superior de Ingeniería y Sistemas de Telecomunicación. Actualmente se ha encontrado alguna dificultad para poder aplicar los algoritmos ya que se han ido desarrollando a lo largo de varios años, por distintas personas y en distintos entornos de programación. Se han adaptado los programas existentes para generar una única herramienta en MATLAB que permite: . Detección de voz . Detección sordo/sonoro . Extracción y revisión manual de frecuencia fundamental de los sonidos sonoros . Extracción y revisión manual de formantes de los sonidos sonoros En todos los casos el usuario puede ajustar los parámetros de análisis y se ha mantenido y, en algunos casos, ampliado la funcionalidad de los algoritmos existentes. Los resultados del análisis se pueden manejar directamente en la aplicación o guardarse en un fichero. Por último se ha escrito el manual de usuario de la aplicación y se ha generado una aplicación independiente que puede instalarse y ejecutarse aunque no se disponga del software o de la versión adecuada de MATLAB. ABSTRACT. The speech is the main communication tool which has the human that as well as allowing to express his thoughts and feelings distinguishes him as an individual. The analysis of speech signal is essential for multiple applications such as: synthesis and recognition of speech, coding, detection of pathologies, identification and speaker recognition… In the market you can find commercial or open source tools to perform this task. The aim of this Final Degree Project is collect several algorithms of speech signal analysis in a single tool which will be managed through a graphical environment. These algorithms are being used in the research group Aplicaciones MultiMedia y Acústica at the Universidad Politécnica de Madrid to carry out its research work and to offer training workshops for students at the Escuela Técnica Superior de Ingeniería y Sistemas de Telecomunicación. Currently some difficulty has been found to be able to apply the algorithms as they have been developing over several years, by different people and in different programming environments. Existing programs have been adapted to generate a single tool in MATLAB that allows: . Voice Detection . Voice/Unvoice Detection . Extraction and manual review of fundamental frequency of voiced sounds . Extraction and manual review formant voiced sounds In all cases the user can adjust the scan settings, we have maintained and in some cases expanded the functionality of existing algorithms. The analysis results can be managed directly in the application or saved to a file. Finally we have written the application user’s manual and it has generated a standalone application that can be installed and run although the user does not have MATLAB software or the appropriate version.

Evaluation of complex temporal questions in CLEF-QA

This paper presents the evaluation of a QA system for the treatment of complex temporal questions. The system was implemented in a multilayered architecture where complex temporal questions are first decomposed into simple questions, according to the temporal relations expressed in the original question. These simple questions are then processed independently by our standard Question Answering engine and their respective answers are filtered to satisfy the temporal restrictions of each simple question. The answers to the simple decomposed questions are then combined, according to the temporal relations extracted from the original complex question, to give the final answer. This evaluation was performed as a pilot task in the Spanish QA Track of the Cross Language Evaluation Forum 2004.

A knowledge-based textual entailment approach applied to the QA answer validation at CLEF 2006

The Answer Validation Exercise (AVE) is a pilot track within the Cross-Language Evaluation Forum (CLEF) 2006. The AVE competition provides an evaluation frame- work for answer validations in Question Answering (QA). In our participation in AVE, we propose a system that has been initially used for other task as Recognising Textual Entailment (RTE). The aim of our participation is to evaluate the improvement our system brings to QA. Moreover, due to the fact that these two task (AVE and RTE) have the same main idea, which is to find semantic implications between two fragments of text, our system has been able to be directly applied to the AVE competition. Our system is based on the representation of the texts by means of logic forms and the computation of semantic comparison between them. This comparison is carried out using two different approaches. The first one managed by a deeper study of the Word- Net relations, and the second uses the measure defined by Lin in order to compute the semantic similarity between the logic form predicates. Moreover, we have also designed a voting strategy between our system and the MLEnt system, also presented by the University of Alicante, with the aim of obtaining a joint execution of the two systems developed at the University of Alicante. Although the results obtained have not been very high, we consider that they are quite promising and this supports the fact that there is still a lot of work on researching in any kind of textual entailment.

A general proposal to multilingual information access based on syntactic-semantic patterns

In the last few years, there has been a wide development in the research on textual information systems. The goal is to improve these systems in order to allow an easy localization, treatment and access to the information stored in digital format (Digital Databases, Documental Databases, and so on). There are lots of applications focused on information access (for example, Web-search systems like Google or Altavista). However, these applications have problems when they must access to cross-language information, or when they need to show information in a language different from the one of the query. This paper explores the use of syntactic-sematic patterns as a method to access to multilingual information, and revise, in the case of Information Retrieval, where it is possible and useful to employ patterns when it comes to the multilingual and interactive aspects. On the one hand, the multilingual aspects that are going to be studied are the ones related to the access to documents in different languages from the one of the query, as well as the automatic translation of the document, i.e. a machine translation system based on patterns. On the other hand, this paper is going to go deep into the interactive aspects related to the reformulation of a query based on the syntactic-semantic pattern of the request.

Using WordNet relations and semantic classes in information retrieval tasks

In this paper we explore the use of semantic classes in an existing information retrieval system in order to improve its results. Thus, we use two different ontologies of semantic classes (WordNet domain and Basic Level Concepts) in order to re-rank the retrieved documents and obtain better recall and precision. Finally, we implement a new method for weighting the expanded terms taking into account the weights of the original query terms and their relations in WordNet with respect to the new ones (which have demonstrated to improve the results). The evaluation of these approaches was carried out in the CLEF Robust-WSD Task, obtaining an improvement of 1.8% in GMAP for the semantic classes approach and 10% in MAP employing the WordNet term weighting approach.

AliQAn, Spanish QA system at multilingual QA@CLEF-2008

Comunicación presentada en Cross-Language Evaluation Forum (CLEF 2008), Aarhus, Denmark, September 17-19, 2008.

Auditory-visual speech integration by prelinguistic infants: Perception of an emergent consonant in the McGurk effect

The McGurk effect, in which auditory [ba] dubbed onto [go] lip movements is perceived as da or tha, was employed in a real-time task to investigate auditory-visual speech perception in prelingual infants. Experiments 1A and 1B established the validity of real-time dubbing for producing the effect. In Experiment 2, 4(1)/(2)-month-olds were tested in a habituation-test paradigm, in which 2 an auditory-visual stimulus was presented contingent upon visual fixation of a live face. The experimental group was habituated to a McGurk stimulus (auditory [ba] visual [ga]), and the control group to matching auditory-visual [ba]. Each group was then presented with three auditory-only test trials, [ba], [da], and [deltaa] (as in then). Visual-fixation durations in test trials showed that the experimental group treated the emergent percept in the McGurk effect, [da] or [deltaa], as familiar (even though they had not heard these sounds previously) and [ba] as novel. For control group infants [da] and [deltaa] were no more familiar than [ba]. These results are consistent with infants'perception of the McGurk effect, and support the conclusion that prelinguistic infants integrate auditory and visual speech information. (C) 2004 Wiley Periodicals, Inc.