Now showing items 21-40 of 43

    • An adaptive gradient-search based algorithm for discriminative training of hmm's 

      Nogueiras Rodríguez, Albino; Mariño Acebal, José Bernardo; Monte Moreno, Enrique (Robert H. Mannel and Jordi Robert-Ribes, 1998)
      Conference lecture
      Restricted access - publisher's policy
      Although having revealed to be a very powerful tool in acoustic modelling, discriminative training presents a major drawback: the lack of a formulation guaranteeing convergence in no matter which initial conditions, such ...
    • An HMM-Based Approach to the INTERSPEECH 2011 Speaker State Challenge 

      Nogueiras Rodríguez, Albino (2011)
      Conference lecture
      Restricted access - publisher's policy
      The current main trend in paralinguistic information recognition is the so-called static classification. In this kind of classification the low level descriptors are pooled togethr by means of statistical functionals ...
    • Duration modeling with expanded HMM applied to speech recognition 

      Bonafonte Cávez, Antonio; Vidal Manzano, José; Nogueiras Rodríguez, Albino (H. TIMOTHY BRUMMELL, WILLIAM IDSARDI CITATION DELAWARE, NEW CASTLE, DELAWARE, 1996)
      Conference lecture
      Open Access
      The occupancy of the HMM states is modeled by means of a Markov chain. A linear estimator is introduced to compute the probabilities of the Markov chain. The distribution function (DF) represents accurately the observed ...
    • Entrenamiento Disciminativo de Modelos Ocultos de Markov de Unidad Subléxica para su Aplicación a Sistemas de Reconocimiento Automático del Habla Continua 

      Nogueiras Rodríguez, Albino (Universitat Politècnica de Catalunya, 1999-11-22)
      Doctoral thesis
      Open Access
      En esta tesis se aborda el entrenamiento discriminativo de unidades subléxicas utilizando bases de datos de propósito geneal. Las unidades subléxicas son la base de funcionamiento de los sistemas de reconocimiento de grandes ...
    • Examen final del quadrimestre de primavera, curs 2011-2012: enunciat 

      Gasull Llampallas, Antoni; Nogueiras Rodríguez, Albino; Salavedra Molí, Josep; Vallverdú Bayés, Sisco (Universitat Politècnica de Catalunya, 2012-06-15)
      Exam
      Restricted access to the UPC academic community
    • Examen final del quadrimestre de primavera, curs 2012-2013: enunciat 

      Gasull Llampallas, Antoni; Moreno Bilbao, M. Asunción; Nadeu Camprubí, Climent; Nogueiras Rodríguez, Albino; Salavedra Molí, Josep; Sayrol Clols, Elisa; Vallverdú Bayés, Sisco (Universitat Politècnica de Catalunya, 2013-06-21)
      Exam
      Restricted access to the UPC academic community
    • Examen final del quadrimestre de tardor, curs 2011-2012: enunciat 

      Vallverdú Bayés, Sisco; Gasull Llampallas, Antoni; Nogueiras Rodríguez, Albino; Salavedra Molí, Josep (Universitat Politècnica de Catalunya, 2012-01-24)
      Exam
      Restricted access to the UPC academic community
    • Explicit segmentation of speech using gaussian models 

      Bonafonte Cávez, Antonio; Nogueiras Rodríguez, Albino; Rodriguez-Garrido, A (H. TIMOTHY BRUMMELL, WILLIAM IDSARDI CITATION DELAWARE, NEW CASTLE, DELAWARE, 1996)
      Conference report
      Restricted access - publisher's policy
      The authors investigate an automatic method to segment labeled speech. The method needs an initial estimation of the segmentation which is provided by an alignment based on HMM. Afterwards, the boundaries are refined moving ...
    • First experiments on an HMM based double layer framework for automatic continuous speech recognition 

      Nogueiras Rodríguez, Albino; Casar López, Marta; Rodríguez Fonollosa, José Adrián; Caballero Galeote, Mónica (2006)
      Conference lecture
      Restricted access - publisher's policy
      The usual approach to automatic continuous speech recognition is what can be called the acoustic-phonetic modelling approach. In this approach, voice is considered to hold two different kinds of information acoustic and ...
    • Frequency and time filtering of filter-bank energies for HMM speech recognition 

      Nadeu Camprubí, Climent; Mariño Acebal, José Bernardo; Hernando Pericás, Francisco Javier; Nogueiras Rodríguez, Albino (H. TIMOTHY BRUMMELL, WILLIAM IDSARDI CITATION DELAWARE, NEW CASTLE, DELAWARE, 1996)
      Conference lecture
      Restricted access - publisher's policy
      In speech recognition, a discriminative frequency weighting can be achieved by decorrelating the frequency sequence of log mel-scaled filter-bank energies with a computationally inexpensive filter. We show how the spectral ...
    • Joint training of codebooks and acoustic models in automatic speech recognition using semi-continuous HMMs 

      Nogueiras Rodríguez, Albino; Caballero Galeote, Mónica; Mariño Acebal, José Bernardo (Eduardo Lleida Solano, 2006)
      Conference lecture
      Restricted access - publisher's policy
      In this paper, three different techniques for building semicontinuousHMMbased speech recognisers are compared: the classical one, using Euclidean generated codebooks and independently trained acoustic models; jointly ...
    • Maximum likelihood based discriminative training of acoustic models 

      Nogueiras Rodríguez, Albino; Mariño Acebal, José Bernardo (European Speech Communication Association (ESCA), 1995)
      Conference report
      Open Access
      In this paper, a framework for discriminative training of acoustic models based on Generalised Probabilistic Descent (GPD) method is presented. The key feature of our proposal, Maximum Likelihood based Discriminative ...
    • Minimum confusibility training of context dependent demiphones 

      Nogueiras Rodríguez, Albino; Mariño Acebal, José Bernardo (G. Olaszy, G. Németh, K. Erdohegyi, 1999)
      Conference report
      Open Access
      During the last years two different approaches have been widely used in order to improve the acoustic modeling in continuous speech recognition systems: discriminative training algorithms and context dependent subword ...
    • Multi-dialectal Spanish speech recognition 

      Nogueiras Rodríguez, Albino; Caballero Galeote, Mónica; Moreno Bilbao, M. Asunción (Institute of Electrical and Electronics Engineers (IEEE), 2002)
      Conference report
      Restricted access - publisher's policy
      Spanish is a global language, spoken in a big number of different countries with a big dialectal variability‥ This paper deals with the suitability of using a single multi-dialectal acoustic modeling for all the Spanish ...
    • Multidialectal acoustic modeling: a comparative study 

      Caballero Galeote, Mónica; Moreno Bilbao, M. Asunción; Nogueiras Rodríguez, Albino (2006)
      Conference lecture
      Restricted access - publisher's policy
      In this paper, multidialectal acoustic modeling based on shar- ing data across dialects is addressed. A comparative study of different methods of combining data based on decision tree clustering algorithms is presented. ...
    • NaniBD: a set of tools for transcribing and validating speech databases 

      Nogueiras Rodríguez, Albino; Moreno Bilbao, M. Asunción (European Language Resources Association (ELRA), 1998)
      Conference report
      Open Access
      This paper describes NaniBD, a set of tools designed for transcribing and validating speech databases, developed at the Signal Processing Group (GPS) of the Department of Signal Theory and Communications of the Polytechnic ...
    • Ponderación ML de parámetros en un sistema de reconocimiento de palabras basado en CDHMM 

      Valverde Amador, Antonio Javier; Hernando Pericás, Francisco Javier; Nogueiras Rodríguez, Albino (1996)
      Conference lecture
      Open Access
      Speech dynamic feature are routinely used in current speech recognition systems in combination with short-term (static) spectral features. The aim of this paper is to propose a method to automatically estimate the optimum ...
    • SETHOS: the UPC speech understanding system 

      Bonafonte Cávez, Antonio; Mariño Acebal, José Bernardo; Nogueiras Rodríguez, Albino (H. TIMOTHY BRUMMELL, WILLIAM IDSARDI CITATION DELAWARE, NEW CASTLE, DELAWARE, 1996)
      Conference lecture
      Restricted access - publisher's policy
      In EuroSpeech'95, the authors presented the first version of Sethos, the speech understanding system which has been developed at the UPC. In this paper some improvements are incorporated at different levels of Sethos: ...
    • Speech emotion recognition using hidden Markov models 

      Nogueiras Rodríguez, Albino; Mariño Acebal, José Bernardo; Bonafonte Cávez, Antonio; Moreno Bilbao, M. Asunción (2001)
      Conference lecture
      Restricted access - publisher's policy
      This paper introduces a first approach to emotion recognition using RAMSES, the UPC’s speech recognition system. The approach is based on standard speech recognition technology using hidden semi-continuous Markov models. ...
    • Task adaptation of sub-lexical unit models using the minimum confusibility criterion on task independent databases 

      Nogueiras Rodríguez, Albino; Mariño Acebal, José Bernardo (Robert H. Mannel and Jordi Robert-Ribes, 1998)
      Conference lecture
      Restricted access - publisher's policy
      Discriminative training is a powerful tool in acoustic modeling for automatic speech recognition. Its strength is based on the direct minimisation of the number of errors committed by the system at recognition time. This ...