Ara es mostren els items 67-86 de 128

    • La tecnologia de la parla en català: avenços i reptes 

      Rodríguez Fonollosa, José Adrián (2010-07)
      Article
      Accés obert
      L’article brinda un panorama sumari però exhaustiu de la situació de les tecnologies de la parla en català. Una primera part introductòria dóna pas a una relació d’aplicacions i recursos. Finalment, s’aborda el projecte ...
    • Language modelling for speaker diarization in telephonic interviews 

      India Massana, Miquel Àngel; Hernando Pericás, Francisco Javier; Rodríguez Fonollosa, José Adrián (Elsevier, 2023-03)
      Article
      Accés obert
      The aim of this paper is to investigate the benefit of combining both language and acoustic modelling for speaker diarization. Although conventional systems only use acoustic features, in some scenarios linguistic data ...
    • Latest trends in hybrid machine translation and its applications 

      Rodríguez Fonollosa, José Adrián; Ruiz Costa-Jussà, Marta (Elsevier, 2015-07)
      Article
      Accés obert
      This survey on hybrid machine translation (MT) is motivated by the fact that hybridization techniques have become popular as they attempt to combine the best characteristics of highly advanced pure rule or corpus-based MT ...
    • Linguistic knowledge-based vocabularies for Neural Machine Translation 

      Casas Manzanares, Noé; Ruiz Costa-Jussà, Marta; Rodríguez Fonollosa, José Adrián; Alonso, Juan; Fanlo, Ramon (Cambridge University Press, 2020)
      Article
      Accés obert
      Neural Networks applied to Machine Translation need a finite vocabulary to express textual information as a sequence of discrete tokens. The currently dominant subword vocabularies exploit statistically-discovered common ...
    • Linguistic-based evaluation criteria to identify statistical machine translation errors 

      Farrús Cabeceran, Mireia; Ruiz Costa-Jussà, Marta; Mariño Acebal, José Bernardo; Rodríguez Fonollosa, José Adrián (2010-05)
      Comunicació de congrés
      Accés obert
      Machine translation evaluation methods are highly necessary in order to analyze the performance of translation systems. Up to now, the most traditional methods are the use of automatic measures such as BLEU or the ...
    • Low delay phone recognition 

      Rodríguez Fonollosa, José Adrián; Mariño Acebal, José Bernardo (1998)
      Text en actes de congrés
      Accés obert
    • LSTM neural network-based speaker segmentation using acoustic and language modelling 

      India Massana, Miquel Àngel; Rodríguez Fonollosa, José Adrián; Hernando Pericás, Francisco Javier (International Speech Communication Association (ISCA), 2017)
      Comunicació de congrés
      Accés obert
      This paper presents a new speaker change detection system based on Long Short-Term Memory (LSTM) neural networks using acoustic data and linguistic content. Language modelling is combined with two different ...
    • Mail Access Plus. Sistema de Mensajería Unificada 

      Rodríguez Fonollosa, José Adrián; Guillermo, Vila; David, Font (Universidad de Zaragoza. URSI, 2000)
      Text en actes de congrés
      Accés obert
      This paper describes an unified messaging system which joins voice mail, fax and e-mail access. Its architecture consists in a group of independent servers, each offering an interface between the unified mailbox and an ...
    • Measuring acoustic reduction in feature space 

      Rodríguez Fonollosa, José Adrián; Schulz, Henrik (2012)
      Comunicació de congrés
      Accés restringit per política de l'editorial
      Modelling varying speaking style remains a challenge to sta te of the art speech recognition and synthesis systems. Vowel a nd consonant reduction have been identified as correlative to speaking st yle variation, but ...
    • Modelling the effects of spontaneous speech in speech recognition 

      Shulz, Henrik; Rodríguez Fonollosa, José Adrián (2013)
      Text en actes de congrés
      Accés obert
      Intrinsic variability of the speaker in spontaneous speech remains a challenge to state of the art Automatic speech recognition (ASR). While planned speech exhibits a moderate variability, the significant variability ...
    • Modelo estocástico de traducción basado en N-gramas de tuplas bilingues y combinación log-lineal de características  

      Mariño, José B.; Banchs, Rafael E.; Crego, Josep Maria; de Gispert, Adrià; Lambert, Patrik; Rodríguez Fonollosa, José Adrián; Ruiz Costa-Jussà, Marta (2005-09-01)
      Article
      Accés restringit per política de l'editorial
      En esta comunicación se presenta un sistema de traducción estocástica basado en el modelado mediante N-gramas de la probabilidad conjunta de textos bilingües. La unidad básica del modelo es la tupla, par de cadenas de ...
    • Multilingual machine translation: Closing the gap between shared and language-specific encoder-decoders 

      Escolano Peinado, Carlos; Ruiz Costa-Jussà, Marta; Rodríguez Fonollosa, José Adrián; Artetxe Zurutuza, Mikel (Association for Computational Linguistics, 2021)
      Comunicació de congrés
      Accés obert
      State-of-the-art multilingual machine translation relies on a universal encoder-decoder, which requires retraining the entire system to add new languages. In this paper, we propose an alternative approach that is based on ...
    • Multilingual machine translation: Deep analysis of language-specific encoder-decoders 

      Escolano Peinado, Carlos; Ruiz Costa-Jussà, Marta; Rodríguez Fonollosa, José Adrián (2022-04-25)
      Article
      Accés obert
      State-of-the-art multilingual machine translation relies on a shared encoder-decoder. In this paper, we propose an alternative approach based on language-specific encoder-decoders, which can be easily extended to new ...
    • N-gram-based Machine Translation 

      Mariño Acebal, José Bernardo; Banchs Martínez, Rafael Enrique; Crego Clemente, Josep Maria; Gispert Brosa, Adrian de; Lambert, Patrik; Rodríguez Fonollosa, José Adrián; Ruiz Costa-Jussà, Marta (2006-12)
      Article
      Accés obert
      This article describes in detail an n-gram approach to statistical machine translation. This approach consists of a log-linear combination of a translation model based on n-grams of bilingual units, which are referred to ...
    • N-gram-based statistical machine translation versus syntax augmented machine translation: comparison and system combination 

      Khalilov, Maxim; Rodríguez Fonollosa, José Adrián (2009-03-30)
      Comunicació de congrés
      Accés obert
      In this paper we compare and contrast two approaches to Machine Translation (MT): the CMU-UKA Syntax Augmented Machine Translation system (SAMT) and UPC-TALP N-gram-based Statistical Machine Translation (SMT). SAMT ...
    • Nanitrans: a speech labelling tool 

      Portabella, D; Febrer, A; Moreno Bilbao, M. Asunción; Rodríguez Fonollosa, José Adrián (., 2000)
      Text en actes de congrés
      Accés obert
      This paper deals with a description of NaniTrans, a tool for segmentation and labeling of speech. The tool is programmed to work on the MATLAB application interface, in any of the supported platforms (Unix, Windows, ...
    • Neural machine translation using bitmap fonts 

      Aldón Mínguez, David; Ruiz Costa-Jussà, Marta; Rodríguez Fonollosa, José Adrián (2016)
      Comunicació de congrés
      Accés obert
      Recently, translation systems based on neural networks are starting to compete with systems based on phrases. The systems which are based on neural networks use vectorial repre- sentations of words. However, one of the ...
    • Neural network language models to select the best translation 

      Khalilov, Maxim; Rodríguez Fonollosa, José Adrián; Zamora Martínez, Francisco; Castro Bleda, María José; España Boquera, Salvador (2013-12-20)
      Article
      Accés obert
      The quality of translations produced by statistical machine translation (SMT) systems crucially depends on the generalization ability provided by the statistical models involved in the process. While most modern SMT ...
    • New hos-based parameter estimation methods for speech recognition in noisy environments 

      Moreno Bilbao, M. Asunción; Tortola, S; Vidal Manzano, José; Rodríguez Fonollosa, José Adrián (. S.N., 1995)
      Text en actes de congrés
      Accés obert
      The problem of recognition in noisy environments is addressed. Often, a recognition system is used in a noisy environment and there is no possibility of training it with noisy samples. Classical speech analysis techniques ...
    • On the adaptive lattice algorithms with data dependent parameters 

      Masgrau Gómez, Enrique José; Rodríguez Fonollosa, José Adrián (1990)
      Text en actes de congrés
      Accés obert