Exploració per autor "Pachès Leal, Pau"

Ara es mostren els items 1-5 de 5

    • Filtering the time sequence of spectral parameters for speaker-independent CDHMM word recognition. 

      Nadeu Camprubí, Climent; Pachès Leal, Pau; Juang, B H (ESCA - J.M. PARDO, E. ENRIQUEZ, J. ORTEGA, J. FERREIROS GTM-UPM, 1995)
      Text en actes de congrés
      Accés obert
      In this work, we show how speaker-independent CDHMM word recognition performance can be significantly improved for clean speech by filtering the time sequence of spectral parameters to enhance its time dynamics. Experimental ...

    • Filtering the time sequences of spectral parameters for speech recognition 

      Nadeu Camprubí, Climent; Pachès Leal, Pau; Biing-Hwang, Juang (1997-09)
      Article
      Accés restringit per política de l'editorial
      In automatic speech recognition, the signal is usually represented by a set of time sequences of spectral parameters (TSSPs) that model the temporal evolution of the spectral envelope frame-to-frame. Those sequences are ...

    • On parameter filtering in continuous subword-unit-based speech recognition 

      Pachès Leal, Pau; Nadeu Camprubí, Climent (H. TIMOTHY BRUMMELL, WILLIAM IDSARDI CITATION DELAWARE, NEW CASTLE, DELAWARE, 1996)
      Text en actes de congrés
      Accés obert
      Simple IIR or FIR filters have been widely used in isolated or connected word recognition tasks to filter the time sequence of speech spectral parameters, since, despite their simplicity, they significantly improve recognition ...

    • Optimization algorithms for estimating modulation spectrum domain filters 

      Pachès Leal, Pau; Rose, R; Nadeu Camprubí, Climent (G. Olaszy, G. Németh, K. Erdohegyi, 1999)
      Text en actes de congrés
      Accés obert
      The goal of the work described in this paper is to develop and evaluate procedures for automatic estimation of modulation spectrum filters to compensate for distortions in the modulation spectrum domain. The modulation ...

    • The demiphone: An efficient contextual subword unit for continuous speech recognition 

      Mariño Acebal, José Bernardo; Nogueiras Rodríguez, Albino; Pachès Leal, Pau; Bonafonte Cávez, Antonio (2000-09)
      Article
      Accés restringit per política de l'editorial
      In this paper, we introduce the demiphone as a context-dependent phonetic unit for continuous speech recognition. A phoneme is divided into two parts: a left demiphone that accounts for the left coarticulation and a right ...