Ara es mostren els items 79-98 de 133

    • Real-time GPU-based face detection in HD video sequences 

      Oro, David; Fernández, Carles; Rodriguez Saeta, Javier; Martorell Bofill, Xavier; Hernando Pericás, Francisco Javier (2011)
      Comunicació de congrés
      Accés restringit per política de l'editorial
      Modern GPUs have evolved into fully programmable parallel stream multiprocessors. Due to the nature of the graphic workloads, computer vision algorithms are in good position to leverage the computing power of these ...
    • Reconocimiento del habla en ambientes ruidosos mediante modelos ocultos de Markov discretos 

      Hernando Pericás, Francisco Javier; Nadeu Camprubí, Climent (1992)
      Text en actes de congrés
      Accés obert
      Speech recognition in noisy environments remains an unsolved problem, even in the case of isolated word recognition with small vocabularies. Recently, several techniques have been proposed to alleviate this problem. ...
    • Reconocimiento del locutor en telefonia: actividades del proyecto europeo COST 250 

      Hernando Pericás, Francisco Javier; Garcia, C; Rodriguez, L; González Rodríguez, Joaquin; Ortega García, Javier (Universidad Politecnica de Madrid, 2000)
      Text en actes de congrés
      Accés obert
      El objetivo de esta comunicación es presentar las actividades realizadas desde noviembre de 1994 dentro del proyecto “Speaker Recognition in Telephony”, financiado por la Comunidad Europea en el marco del programa “European ...
    • Reconocimiento del locutor mediante filtrado frecuencial de energías espectrales estimadas por métodos híbridos 

      Hernando Pericás, Francisco Javier; Nadeu Camprubí, Climent (Universidad Politecnica de Madrid, 2000)
      Text en actes de congrés
      Accés obert
      Se han explorado dos formas de obtener parámetros más robustos para reconocimiento del locutor: la hibridación de técnicas de análisis espectral y el filtrado frecuencial de las energías de las bandas. Se ha comprobado que ...
    • Reconocimiento robusto del habla en presencia de ruido de coche 

      Hernando Pericás, Francisco Javier; Nadeu Camprubí, Climent (1993)
      Text en actes de congrés
      Accés obert
      The performance of existing speech recognition systems degrades rapidly in the presence of background noise when training and testing cannot be done under the same ambient conditions. The aim of this paper is to report the ...
    • Restricted Boltzmann Machine Supervectors for speaker recognition 

      Ghahabi Esfahani, Omid; Hernando Pericás, Francisco Javier (Institute of Electrical and Electronics Engineers (IEEE), 2015)
      Text en actes de congrés
      Accés restringit per política de l'editorial
      The use of Restricted Boltzmann Machines (RBM) is proposed in this paper as a non-linear transformation of GMM supervectors for speaker recognition. It will be shown that the RBM transformation will increase the discrimination ...
    • Restricted Boltzmann Machine vectors for speaker clustering 

      Khan, Umair; Safari, Pooyan; Hernando Pericás, Francisco Javier (International Speech Communication Association (ISCA), 2018)
      Comunicació de congrés
      Accés obert
      Restricted Boltzmann Machines (RBMs) have been used both in the front-end and backend of speaker verification systems. In this work, we apply RBMs as a front-end in the context of speaker clustering. Speakers' utterances ...
    • Restricted Boltzmann machine vectors for speaker clustering and tracking tasks in TV broadcast shows 

      Khan, Umair; Safari, Pooyan; Hernando Pericás, Francisco Javier (Multidisciplinary Digital Publishing Institute, 2019-07-09)
      Article
      Accés obert
      Restricted Boltzmann Machines (RBMs) have shown success in both the front-end and backend of speaker verification systems. In this paper, we propose applying RBMs to the front-end for the tasks of speaker clustering and ...
    • Restricted Boltzmann machines for vector representation of speech in speaker recognition 

      Ghahabi Esfahani, Omid; Hernando Pericás, Francisco Javier (Elsevier, 2018-01)
      Article
      Accés obert
      Over the last few years, i-vectors have been the state-of-the-art technique in speaker recognition. Recent advances in Deep Learning (DL) technology have improved the quality of i-vectors but the DL techniques in use are ...
    • Robust HOS-based techniques applied to speech recognition and enchancement 

      Salavedra Molí, Josep; Hernando Pericás, Francisco Javier; Masgrau Gómez, Enrique José; Moreno Bilbao, M. Asunción (1995)
      Text en actes de congrés
      Accés obert
      We study some speech enhancement algorithms based on the iterative Wiener filtering method due to Lim-Oppenheim [2], where the AR spectral estimation of the speech is carried out using a second-order analysis. But in our ...
    • Robust hos-based techniques applied to speech recognition and enhancement 

      Salavedra Molí, Josep; Hernando Pericás, Francisco Javier; Masgrau Gómez, Enrique José; Moreno Bilbao, M. Asunción (1995)
      Text en actes de congrés
      Accés obert
      We study some speech enhancement algorithms based on the iterative Wiener filtering method due to Lim-Oppenheim [2], where the AR spectral estimation of the speech is carried out using a second-order analysis. But in our ...
    • Robust speech parameters located in the frequency domain 

      Hernando Pericás, Francisco Javier; Nadeu Camprubí, Climent (1997)
      Text en actes de congrés
      Accés obert
      In this paper, two ways of obtaining more robust spectral parameters are explored. Firstly, an hybridization of both LP and filter-bank approaches is considered, which is capable of improving recognition results for both ...
    • Self attention networks in speaker recognition 

      Safari, Pooyan; India Massana, Miquel Àngel; Hernando Pericás, Francisco Javier (Multidisciplinary Digital Publishing Institute, 2023-05-24)
      Article
      Accés obert
      Recently, there has been a significant surge of interest in Self-Attention Networks (SANs) based on the Transformer architecture. This can be attributed to their notable ability for parallelization and their impressive ...
    • Self multi-head attention for speaker recognition 

      India Massana, Miquel Àngel; Safari, Pooyan; Hernando Pericás, Francisco Javier (International Speech Communication Association (ISCA), 2019)
      Comunicació de congrés
      Accés obert
      Most state-of-the-art Deep Learning (DL) approaches forspeaker recognition work on a short utterance level. Given thespeech signal, these algorithms extract a sequence of speakerembeddings from short segments and those are ...
    • Self-attention encoding and pooling for speaker recognition 

      Safari, Pooyan; India Massana, Miquel Àngel; Hernando Pericás, Francisco Javier (International Speech Communication Association (ISCA), 2020)
      Text en actes de congrés
      Accés obert
      The computing power of mobile devices limits the end-user applications in terms of storage size, processing, memory and energy consumption. These limitations motivate researchers for the design of more efficient deep models. ...
    • Self-supervised deep learning approaches to speaker recognition: A Ph.D. Thesis overview 

      Khan, Umair; Hernando Pericás, Francisco Javier (International Speech Communication Association (ISCA), 2021)
      Comunicació de congrés
      Accés obert
      Recent advances in Deep Learning (DL) for speaker recognition have improved the performance but are constrained to the need of labels for the background data, which is difficult in prac- tice. In i-vector based speaker ...
    • Short- and long-term speech features for hybrid HMM-i-vector based speaker diarization system 

      Zewoudie, Abraham Woubie; Luque, Jordi; Hernando Pericás, Francisco Javier (2016)
      Comunicació de congrés
      Accés obert
      i-vectors have been successfully applied over the last years in speaker recognition tasks. This work aims at assessing the suitability of i-vector modeling within the frame of speaker diarization task. In such context, a ...
    • Simultaneous speech detection with spatial features for speaker diarization 

      Zelenak, Martin; Segura Perales, Carlos; Luque, Jordi; Hernando Pericás, Francisco Javier (2012-02)
      Article
      Accés restringit per política de l'editorial
      Simultaneous speech poses a challenging problem for conventional speaker diarization systems. In meeting data, a substantial amount of missed speech error is due to speaker overlaps, since usually only one speaker label ...
    • Some fast higher order ar estimation techniques applied to parametric wiener filtering 

      Salavedra Molí, Josep; Masgrau Gómez, Enrique José; Moreno Bilbao, M. Asunción; Estarellas, J; Hernando Pericás, Francisco Javier (2004)
      Text en actes de congrés
      Accés obert
      Some Speech Enhancement algorithms based on the iterative Wiener filtering Method due to L1m-Oppenheim [2] are presented. In the original Lim-Oppenheim algorithm, speech AR estimation is carried out using classic second-order ...
    • Speaker characterization by means of attention pooling 

      Costa, Federico; India Massana, Miquel Àngel; Hernando Pericás, Francisco Javier (International Speech Communication Association (ISCA), 2022)
      Comunicació de congrés
      Accés obert
      State-of-the-art Deep Learning systems for speaker verification are commonly based on speaker embedding extractors. These architectures are usually composed of a feature extractor front-end together with a pooling layer ...