- -

Listar por autor "Andrés Ferrer, Jesús"

RiuNet: Repositorio Institucional de la Universidad Politécnica de Valencia

Listar por autor "Andrés Ferrer, Jesús"

Ordenar por:Orden:Resultados:

  • thumb
    Adaptació dels models de llenguatge per a la transcripció de vídeos de poli[Media] 
    Martínez Villaronga, Adrià Agustí (Universitat Politècnica de València, 2012-07-30)
    Al llarg del darrer segle la forma de consumir la informació ha canviat de forma important. Mentre que a principis del segle XX, tot i l' incipient aparició de la cinematografia, gairebé tots els mitjans eren escrits, ...
  • thumb
    Adaptació massiva dels models de llenguatge en transcripció de vídeo-xarrades 
    Piqueras Gozalbes, Santiago Romualdo (Universitat Politècnica de València, 2013-07-31)
    És difícil negar que visquem en un món d' informació. Els avançaments científics produïts en les últimes dècades han facilitat l' accés a la mateixa a gran part de la població. Dins de l'espiral d' informació, i especialment ...
  • thumb
    Albayzin Evaluation: The PRHLT-UPV Audio Segmentation System 
    Silvestre Cerdà, Joan Albert; Giménez Pastor, Adrián; Andrés Ferrer, Jesús; Civera Saiz, Jorge; Juan Císcar, Alfonso (Ramos Castro, Daniel, 2012-11-21)
    This paper describes the audio segmentation system developed by the PRHLT research group at the UPV for the Albayzin Audio Segmentation Evaluation 2012. The PRHLT-UPV audio segmentation system is based on a conventional ...
  • thumb
    Aportacions a la millora d'un sistema interactiu d'ajuda a la traducció basat en mètodes estadístics 
    Silvestre Cerdà, Joan Albert (Universitat Politècnica de València, 2011-01-10)
    El propòsit d'aquest treball és, doncs, millorar les prestacions d'aquests sistemes. S'han plantejat una sèrie de millores que afecten directament al sistema de traducció automàtica subjacent, ja que és aquest el que ...
  • thumb
    Arabic Printed Word Recognition Using Windowed Bernoulli HMMs 
    Alkhoury, Ihab; Giménez Pastor, Adrián; Juan Císcar, Alfonso; Andrés Ferrer, Jesús (Springer Verlag, 2013-09-09)
    [EN] Hidden Markov Models (HMMs) are now widely used for off-line text recognition in many languages and, in particular, Arabic. In previous work, we proposed to directly use columns of raw, binary image pixels, which are ...
  • thumb
    Arabic Text Recognition and Machine Translation 
    Alkhoury, Ihab (Universitat Politècnica de València, 2015-07-13)
    [EN] Research on Arabic Handwritten Text Recognition (HTR) and Arabic-English Machine Translation (MT) has been usually approached as two independent areas of study. However, the idea of creating one system that combines ...
  • thumb
    Bernoulli HMMs for Handwritten Text Recognition 
    Giménez Pastor, Adrián (Universitat Politècnica de València, 2014-06-09)
    In last years Hidden Markov Models (HMMs) have received significant attention in the task off-line handwritten text recognition (HTR). As in automatic speech recognition (ASR), HMMs are used to model the probability of ...
  • thumb
    Comparison of Bernoulli and Gaussian HMMs using a vertical repositioning technique for off-line handwriting recognition 
    Doetsch, Patrick; Hamdani, Mahdi; Ney, Hermann; Giménez Pastor, Adrián; Andrés Ferrer, Jesús; Juan Císcar, Alfonso (Institute of Electrical and Electronics Engineers (IEEE), 2012-09-18)
    —In this paper a vertical repositioning method based on the center of gravity is investigated for handwriting recognition systems and evaluated on databases containing Arabic and French handwriting. Experiments show ...
  • thumb
    Competencia en comunicación oral. Un reto para el ingeniero 
    Hermosilla Gómez, Zuriñe; Clemente Císcar, Mónica; Trinidad Tornel, Ángel; Andrés Ferrer, Jesús (Universidad Politécnica de Valencia, 2013-05-06)
    [ES] Un ingeniero no trabaja aislado del resto del mundo. La competencia en comunicación oral es una capacidad que debería incluirse tanto en la educación primaria como secundaria, pero vistas las deficiencias, es necesario ...
  • thumb
    Constrained domain maximum likelihood estimation and the loss function in statistical pattern recognition 
    Andrés Ferrer, Jesús (Universitat Politècnica de València, 2011-11-28)
    In this thesis we present a new estimation algorithm for statistical models which does not incurs in the over-trainning problems. This new estimation techinque, the so-called, constrained domain maximum likelihood estimation ...
  • thumb
    Discriminative Bernoulli HMMs for isolated handwritten word recognition 
    Giménez Pastor, Adrián; Andrés Ferrer, Jesús; Juan, Alfons (Elsevier, 2014-01-01)
    [EN] Bernoulli HMMs (BHMMs) have been successfully applied to handwritten text recognition (HTR) tasks such as continuous and isolated handwritten words. BHMMs belong to the generative model family and, hence, are usually ...
  • thumb
    Discriminative Bernoulli Mixture Models for Handwritten Digit Recognition 
    Giménez Pastor, Adrián; Andrés Ferrer, Jesús; Juan Císcar, Alfonso; Serrano Martinez Santos, Nicolas (Institute of Electrical and Electronics Engineers (IEEE), 2011-09-18)
    Bernoulli-based models such as Bernoulli mixtures or Bernoulli HMMs (BHMMs), have been successfully applied to several handwritten text recognition (HTR) tasks which range from character recognition to continuous and ...
  • thumb
    Does more data always yield better translations? 
    Gascó Mora, Guillem; Rocha Sánchez, Martha Alicia; Sanchis Trilles, Germán; Andrés Ferrer, Jesús; Casacuberta Nolla, Francisco (Association for Computational Linguistics, 2012-04-23)
    Nowadays, there are large amounts of data available to train statistical machine translation systems. However, it is not clear whether all the training data actually help or not. A system trained on a subset of such huge ...
  • thumb
    El uso de rúbricas para una evaluación justa y objetiva en asignaturas prácticas de enseñanzas técnicas y su repercusión en el aprendizaje 
    Alfaro Cid, Eva; Andrés Ferrer, Jesús; Montalva Subirats, José Miguel; Pérez de los Cobos Cassinello, Marta (Universidad Politécnica de Valencia, 2013-05-06)
    [ES] En el nuevo marco de Enseñanza Superior Europeo la evaluación ha pasado de ser una herramienta de control del alumno a una parte más del proceso de aprendizaje. De hecho, una buena evaluación debe estar alineada con ...
  • Icon
    Explicit length modelling for statistical machine translation 
    Silvestre Cerdà, Joan Albert; Andrés Ferrer, Jesús; Civera Saiz, Jorge (Springer Verlag (Germany), 2011)
    Explicit length modelling has been previously explored in statistical pattern recognition with successful results. In this paper, two length models along with two parameter estimation methods for statistical machine ...
  • thumb
    Explicit length modelling for statistical machine translation 
    Silvestre Cerdà, Joan Albert; Andrés Ferrer, Jesús; Civera Saiz, Jorge (Elsevier, 2012)
    [EN] Explicit length modelling has been previously explored in statistical pattern recognition with successful results. In this paper, two length models along with two parameter estimation methods and two alternative ...
  • thumb
    Handwriting word recognition using windowed Bernoulli HMMs 
    Giménez Pastor, Adrián; Alkhoury, Ihab; Andrés Ferrer, Jesús; Juan Císcar, Alfonso (Elsevier, 2014-01)
    [EN] Hidden Markov Models (HMMs) are now widely used for off-line handwriting recognition in many lan- guages. As in speech recognition, they are usually built from shared, embedded HMMs at symbol level, where state-conditional ...
  • thumb
    Language model adaptation for lecture transcription by document retrieval 
    Martínez-Villaronga, Adrià; Del Agua Teba, Miguel Angel; Silvestre Cerdà, Joan Albert; Andrés Ferrer, Jesús; Juan, Alfons (Springer Verlag (Germany), 2014)
    With the spread of MOOCs and video lecture repositories it is more important than ever to have accurate methods for automatically transcribing video lectures. In this work, we propose a simple yet effective language model ...
  • thumb
    Language model adaptation for video lecture transcription 
    Martínez Villaronga, Adrià Agustí (Universitat Politècnica de València, 2014-04-23)
    [ES] En este trabajo proponemos un método de adaptación de modelos de lenguaje a charlas docentes en el contexto de la transcripción automática de videos docentes. Examinaremos diferentes variaciones de la técnica de ...
  • thumb
    Language model adaptation for video lectures transcription 
    Martínez-Villaronga, Adrià; Del Agua Teba, Miguel Angel; Andrés Ferrer, Jesús; Juan Císcar, Alfonso (IInstitute of Electrical and Electronics Engineers (IEEE), 2013)
    Videolectures are currently being digitised all over the world for its enormous value as reference resource. Many of these lectures are accompanied with slides. The slides offer a great opportunity for improving ASR systems ...