L'àmbit de recerca del grup 'VEU' és el tractament de la parla. Investiguem tecnologies que permeten l'extracció d'informació que la veu conté: reconeixement del que es diu, l'idioma o el dialecte, característiques del parlant -qui és, la seva edat, el sexe, l'estat emocional-, la direcció del so. També treballem en la caracterització general de l'àudio, per determinar quan hi ha veu i quan hi ha altres esdeveniments acústics com música o sorolls diversos. Les tecnologies de la parla possibiliten generar veu -síntesis de veu- o modificar les seves

Recent Submissions

  • Gender bias in multilingual neural machine translation: The architecture matters 

    Ruiz Costa-Jussà, Marta; Escolano Peinado, Carlos; Basta, Christine Raouf Saad; Ferrando Monsonís, Javier; Batlle, Roser; Kharitonova, Ksenia (2020-12-24)
    External research report
    Open Access
    Multilingual Neural Machine Translation architectures mainly differ in the amount of sharing modules and parameters among languages. In this paper, and from an algorithmic perspective, we explore if the chosen architecture, ...
  • Semantic and syntactic information for neural machine translation: Injecting features to the transformer 

    Armengol Estapé, Jordi; Ruiz Costa-Jussà, Marta (2021-05-18)
    Article
    Open Access
    Introducing factors such as linguistic features has long been proposed in machine translation to improve the quality of translations. More recently, factored machine translation has proven to still be useful in the case ...
  • Double multi-head attention for speaker verification 

    India Massana, Miquel Àngel; Safari, Pooyan; Hernando Pericás, Francisco Javier (Institute of Electrical and Electronics Engineers (IEEE), 2021)
    Conference report
    Open Access
    Most state-of-the-art Deep Learning systems for text-independent speaker verification are based on speaker embedding extractors. These architectures are commonly composed of a feature extractor front-end together with a ...
  • Real-time interpolation of global ionospheric maps by means of sparse representation 

    Yang, Heng; Monte Moreno, Enrique; Hernández Pajares, Manuel; Roma Dollase, David (2021-06-12)
    Article
    Restricted access - publisher's policy
    In this paper, we propose a method for the generation of real-time global ionospheric map (RT-GIM) of vertical total electron content (VTEC) from GNSS measurements. The need for interpolation arises from the fact that the ...
  • 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)
    Conference lecture
    Open Access
    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 natural language processing: Towards universal translation 

    Ruiz Costa-Jussà, Marta (Springer Nature, 2021-05)
    Article
    Restricted access - publisher's policy
    State of the art neural network approaches enable massive multilingual translation. How close are we to universal translation in any language?
  • An analysis of gender bias studies in natural language processing 

    Ruiz Costa-Jussà, Marta (Springer Science and Business Media LLC, 2019-10-14)
    Article
    Open Access
    Artificial intelligence systems copy and amplify existing societal biases, a problem that by now is widely acknowledged and studied. But is current research of gender bias in natural language processing actually moving ...
  • The TALP-UPC system for the WMT similar language task: statistical vs neural machine translation 

    Biesialska, Magdalena Marta; Guàrdia Fernández, Lluís; Ruiz Costa-Jussà, Marta (Association for Computational Linguistics, 2019)
    Conference lecture
    Open Access
    Although the problem of similar language translation has been an area of research interest for many years, yet it is still far from being solved. In this paper, we study the performance of two popular approaches: statistical ...
  • Refinement of unsupervised cross-lingual word embeddings 

    Biesialska, Magdalena Marta; Ruiz Costa-Jussà, Marta (Ios Press, 2020)
    Conference lecture
    Open Access
    Cross-lingual word embeddings aim to bridge the gap between high-resource and low-resource languages by allowing to learn multilingual word representations even without using any direct bilingual signal. The lion's share ...
  • Polar electron content from GPS data-based global ionospheric maps: assessment, case studies, and climatology 

    Lyu, Haixia; Hernández Pajares, Manuel; Aragón Ángel, Maria Angeles; Monte Moreno, Enrique; An, Jiachun; Liu, Jingbin (2020-04-22)
    Article
    Open Access
    The electron content distribution of the north and south polar ionosphere from 2001 to the beginning of 2019 is analyzed by using the UQRG global ionospheric map (GIM) of vertical total electron content (VTEC), computed ...
  • Estimation of polar depletion regions by VTEC contrast and watershed enhancing 

    Monte Moreno, Enrique; Hernández Pajares, Manuel; Lyu, Haixia; Yang, Heng; Aragon-Angel, Angela (Institute of Electrical and Electronics Engineers (IEEE), 2021)
    Article
    Open Access
    This article presents a method for determining near-Pole ionization depletion regions and troughs from global navigation satellite system (GNSS) vertical total electron content (VTEC) maps. To define the regions, we use ...
  • Frequency domain analysis and filtering of business and consumer survey expectations 

    Claveria González, Oscar; Monte Moreno, Enrique; Torra Porras, Salvador (Elsevier, 2021-08)
    Article
    Restricted access - publisher's policy
    The main objective of this study is two-fold. First, we aim to detect the underlying existing periodicities in business and consumer survey expectations by means of spectral analysis. We use the Welch method to extract the ...

View more