Browsing by Author "Nogueiras Rodríguez, Albino"Més informacióMés informació

Now showing items 1-20 of 21

  • 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 ...

  • A statistical approach to reverberation in non-diffusive rectangular rooms based on the image source model 

    Nogueiras Rodríguez, Albino; Colom Olivares, Jordi (Institute of Electrical and Electronics Engineers (IEEE), 2013)
    Conference lecture
    Restricted access - publisher's policy
    In this paper, a novel procedure for the estimation of the energy decay curve of the reverberation on rectangular non-diffusive rooms is presented. It is based on the calculation of the expected sound intensity using a ...

  • 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 ...

  • 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 ...

  • 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. ...

  • 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 ...

  • 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 ...

  • Task independent minimum confusability training for continuous speech recognition 

    Nogueiras Rodríguez, Albino; Mariño Acebal, José Bernardo (1998)
    Conference lecture
    Restricted access - publisher's policy
    In this paper, a task independent discriminative training framework for subword units based continuous speech recognition is presented. Instead of aiming at the optimisation of any task independent figure, say the phone ...

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

    Mariño Acebal, José Bernardo; Nogueiras Rodríguez, Albino; Pachés-Leal, Pau; Bonafonte Cávez, Antonio (2000-09)
    Article
    Restricted access - publisher's policy
    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 ...