Now showing items 1-20 of 430

  • A connectionist approach to speech recognition using peripheral auditory modelling 

    Terry, Mark; Renals, Steve; Rohwer, Richard; Harrington, Jonathan (IEEE, 1988-04)
    A prototype isolated word recogniser was constructed, with an auditory-based analysis component and a pattern classification module based on a parallel distributed processing paradigm. The auditory model used was a band-pass ...
  • Unstable connectionist networks in speech recognition 

    Rohwer, Richard; Renals, Steve; Terry, Mark (IEEE, 1988-04)
    Connectionist networks evolve in time according to a prescribed rule. Typically, they are designed to be stable so that their temporal activity ceases after a short transient period. However, meaningful patterns in speech ...
  • Finite state machines from feature grammars 

    Black, Alan W (1989)
    This paper describes the conversion of a set of feature grammar rules into a deterministic finite state machine that accepts the same language (or at least a well-defined related language).
  • Radial basis function network for speech pattern classification 

    Renals, Steve (IEE, 1989-03)
    A neural network model incorporating radial basis functions is used in a speech-pattern classification problem. The method is compared with a back-propagation neural network model and with a vector-quantised hidden Markov ...
  • Duration, Pitch and Diphones in the CSTR TTS System 

    Campbell, Nick; Isard, Stephen; Monaghan, Alex; Verhoeven, J. (International Speech Communication Association, 1990-11)
    This paper describes the prosodic processing and wave-form generation components of the text-to-speech system being developed at Edinburgh University's Centre for Speech Technology Research. Intonation is specified as a ...
  • Analysis of unknown words through morphological decomposition. 

    van de Plassche, J; Black, Alan W (1991)
    This paper describes a method of analysing words through morphological decomposition when the lexicon is incomplete. The method is used within a text-to-speech system to help generate pronunciations of unknown words. The ...
  • Probability estimation by feed-forward networks in continuous speech recognition. 

    Renals, Steve; Morgan, Nelson; Bourlard, Herve (IEEE, 1991)
  • Criteria for labelling prosodic aspects of English speech 

    Bagshaw, Paul C (1992)
    An algorithm is described to abstract acoustic parameters of a speech waveform to give a scalar measure of the relative stress and pitch movement of each group of phones which can consist of a single prominence. A method ...
  • CDNN: a context dependent neural network for continuous speech recognition 

    Bourlard, Herve; Morgan, Nelson; Wooters, Chuck; Renals, Steve (IEEE, 1992-03)
    A series of theoretical and experimental results have suggested that multilayer perceptrons (MLPs) are an effective family of algorithms for the smooth estimate of highly dimensioned probability density functions that are ...
  • Connectionist probability estimation in the DECIPHER speech recognition system 

    Renals, Steve; Morgan, Nelson; Cohen, Michael; Franco, Horacio (IEEE, 1992-03)
    The authors have previously demonstrated that feedforward networks can be used to estimate local output probabilities in hidden Markov model (HMM) speech recognition systems (Renals et al., 1991). These connectionist ...
  • Improving statistical speech recognition 

    Renals, Steve; Morgan, Nelson; Cohen, Michael; Franco, Horacio; Bourlard, Herve (IEEE, 1992-06)
    A summary of the theory of the hybrid connectionist HMM (hidden Markov model) continuous speech recognition system is presented. Experimental results indicating that the connectionist methods can significantly improve the ...
  • Criteria for Labelling Prosodic Aspects of English Speech 

    Bagshaw, Paul C; Williams, Briony (International Speech Communication Association, 1992-10)
    We report a set of labelling criteria which have been developed to label prosodic events in clear, continuous speech, and propose a scheme whereby this information can be transcribed in a machine readable format. We have ...
  • Robust Pitch Detection by Narrow Band Spectrum Analysis 

    Shimodaira, Hiroshi; Nakai, Mitsuru (International Speech Communication Association, 1992-10)
    This paper proposes a new technique for detecting pitch patterns which is useful for automatic speech recognition, by using a narrow band spectrum analysis. The motivation of this approach is that humans perceive some kind ...
  • A New Model of Intonation for Use with Speech Synthesis and Recognition 

    Taylor, Paul A; Isard, Stephen (International Speech Communication Association, 1992-10)
    This paper describes a synthesis from analysis scheme for producing natural sounding intonation for speech synthesis. The paper presents a new method of describing Fo contours in terms of three basic phonetic intonation ...
  • Enhanced pitch tracking and the processing of f0 contours for computer aided intonation teaching. 

    Bagshaw, Paul C; Hiller, S M; Jack, Mervyn A (International Speech Communication Association, 1993)
    A comparative evaluation of several pitch determination algorithms (PDAs) is presented. Fundamental frequency estimates, F0, are compared with laryngeal frequency estimates, Lx. An algorithm is presented which enables Lx ...
  • Phonetic transcription standards for european names (onomastica). 

    Schmidt, Mark; Fitt, Susan; Scott, Christina; Jack, Mervyn A (International Speech Communication Association, 1993)
    This paper details the standards identified for phonetic transcription of names as part of the ONOMASTICA project, a European-wide research initiative for the construction of a multi-language pronunciation lexicon ...
  • Accent phrase segmentation using transition probabilities between pitch pattern templates. 

    Shimodaira, Hiroshi; Nakai, Mitsuru (International Speech Communication Association, 1993)
    This paper proposes a novel method for segmenting continuous speech into accent phrases by using a prosodic feature 'pitch pattern'. The pitch pattern extracted from input speech signals is divided into the accent segments ...
  • Automatic recognition of intonation from F0 contours using the rise/fall/connection model. 

    Taylor, Paul A (International Speech Communication Association, 1993)
    This paper descibes an automatic system for labelling intonational tune information based on the Rise/Fall/Connection model of intonation. The system is powerful in that it presupposes no prosodic knowledge of the utterance ...
  • Synthesizing intonation using the RFC model. 

    Taylor, Paul A (1993)
    This paper describes an implementation of the rise/fall/connection (RFC) model of intonation for use in the speech synthesis component of a machine interpretation system. The phonological input is described, as is the ...
  • Learning temporal dependencies in connectionist speech recognition 

    Renals, Steve; Hochberg, Mike; Robinson, Tony (Morgan Kauffman, 1994)
    Hybrid connectionist/HMM systems model time using both a Markov chain and through properties of a connectionist network. In this paper, we discuss the nature of the time dependence currently employed in our systems using ...