Now showing items 559-578 of 628

  • The THISL Spoken Document Retrieval System 

    Abberley, Dave; Renals, Steve; Cook, Gary; Robinson, Tony (Department of Commerce, National Institute of Standards and Technology, 1998)
    The THISL spoken document retrieval system is based on the Abbot Large Vocabulary Continuous Speech Recognition (LVCSR) system developed by Cambridge University, Sheffield University and SoftSound, and uses PRISE (NIST) ...
  • The THISL system for indexing and retrieval of broadcast news. 

    Renals, Steve; Abberley, Dave; Kirby, David; Robinson, Tony (IEEE, 1999)
    This paper describes the THISL news retrieval system which maintains an archive of BBC radio and television news recordings. The system uses the Abbot large vocabulary continuous speech recognition system to transcribe ...
  • Three Methods of Intonation Modeling 

    Syrdal, Ann; Moehler, Greg; Dusterhoff, Kurt E; Conkie, Alistair; Black, Alan W (International Speech Communication Association, 1998-11)
    This paper compares different methods of generating intonation for an American English Text-to-Speech synthesis system. We look at a primarily rule-based approach and two data-driven approaches. For data-driven modeling ...
  • Threesomes, With and Without Blame 

    Siek, Jeremy; Wadler, Philip (2009)
    The blame calculus of Wadler and Findler gives a high-level semantics to casts in higher-order languages. The coercion calculus of Henglein, on the other hand, provides an instruction set for casts whose normal forms ...
  • The Tilt Intonation Model 

    Taylor, Paul (International Speech Communication Association, 1998-12)
    The tilt intonation model facilitates automatic analysis and synthesis of intonation. The analysis algorithm detects intonational events in F0 contours and parameterises them in terms of the continuously varying parameters. ...
  • To memorize or to predict: Prominence labeling in conversational speech 

    Nenkova, Ani; Brenier, Jason; Kothari, Anubha; Calhoun, Sasha; Whitton, Laura; Beaver, David; Jurafsky, Daniel (2007)
    The immense prosodic variation of natural conversational speech makes it challenging to predict which words are prosodically prominent in this genre. In this paper, we examine a new feature, accent ratio, which captures ...
  • Tongue movement and syllable onset complexity: ultrasound study 

    Kocjancic, Tanja (2008)
    In this study ultrasound was used to investigate tongue movements in syllables with different number and type of onset consonants. Ultrasound recordings provided the information of the distance the tongue travels over a ...
  • Towards a revised model of Code and social regulation 

    Jones, Richard (AHRC Research Centre for Studies in Intellectual Property and Technology Law, 2004-07)
    Paper presented by Jones for the Lefis workshop, Belfast, 2004.
  • Towards a Tailored Sensor Network for Fire Emergency Monitoring in Large Buildings 

    Tsertou, Athanasia; Upadhyay, Rochan; McLaughlin, Stephen; Laurenson, David I (2007)
    Modern fire emergency systems are slowly moving from the traditional data-logging systems to a heterogeneous and dense network of wired/wireless sensors that can give a more complete view of the phenomenon. When the density ...
  • Towards an annotation scheme for noun phrase generation. 

    Poesio, Massimo; Henschel, R; Hitzeman, Janet; Kibble, R; Montague, S; van Deemter, K (European Chapter of the Association for Computational Linguistics, 1999)
    We are studying the feasability of annotating a corpus with information relevant to NP generation, specifically the information needed to decide which type of NP to use. such a corpus might be used just to study correlations ...
  • Towards an improved modeling of the glottal source in statistical parametric speech synthesis 

    Cabral, Joao P; Renals, Steve; Richmond, Korin; Yamagishi, Junichi (2007)
    This paper proposes the use of the Liljencrants-Fant model (LF-model) to represent the glottal source signal in HMM-based speech synthesis systems. These systems generally use a pulse train to model the periodicity of the ...
  • Towards Semi-supervised Manifold Learning: UKR with Structural Hints 

    Steffen, Jan; Klanke, Stefan; Vijayakumar, Sethu; Ritter, Helge (2009)
    We explore generic mechanisms to introduce structural hints into the method of Unsupervised Kernel Regression (UKR) in order to learn representations of data sequences in a semi-supervised way. These new extensions are ...
  • Towards the Hybrid Library: Developments in UK Higher Education 

    Rusbridge, Chris (IFLA, 2000-08)
    The real world in which information professionals struggle to provide high quality services is not the simple world of most so-called "digital library" services, but rather is characterised by complexity and diversity in ...
  • Towards Unsupervised Articulatory Resynthesis of German Utterances using EMA data 

    Steiner, Ingmar; Richmond, Korin (2009)
    As part of ongoing research towards integrating an articulatory synthesizer into a text-to-speech (TTS) framework, a corpus of German utterances recorded with electromagnetic articulography (EMA) is resynthesized to provide ...
  • Tractable nonparametric Bayesian inference in Poisson processes with Gaussian process intensities 

    Adams, Ryan Prescott; Murray, Iain; MacKay, David J. C. (2009)
    The inhomogeneous Poisson process is a point process that has varying intensity across its domain (usually time or space). For nonparametric Bayesian modeling, the Gaussian process is a useful way to place a prior distribution ...
  • A Training Scheme for Pattern Classification Using Multi-layer Feed-forward Neural Networks. 

    Keeni, Kanad; Nakayama, Kenji; Shimodaira, Hiroshi (IEEE, 1999)
    This study highlights on the subject of weight initialization in multi-layer feed-forward networks. Training data is analyzed and the notion of criti- cal point is introduced for determining the initial weights for the ...
  • Trajectory mixture density networks with multiple mixtures for acoustic-articulatory inversion 

    Richmond, Korin (Springer-Verlag Berlin Heidelberg, 2007-12)
    We have previously proposed a trajectory model which is based on a mixture density network (MDN) trained with target variables augmented with dynamic features together with an algorithm for estimating maximum likelihood ...
  • Transcription and Summarization of Voicemail Speech 

    Koumpis, Konstantinos; Renals, Steve (International Speech Communication Association, 2000-10)
    This paper describes the development of a system to transcribe and summarize voicemail messages. The results of the research we present are two-fold. First, a hybrid connectionist approach to the Voicemail transcription ...
  • Transcription of conference room meetings: an investigation 

    Hain, Thomas; Dines, John; Garau, Giulia; Karafiat, Martin; Moore, Darren; Wan, Vincent; Ordelman, Roeland; Renals, Steve (2005)
    The automatic processing of speech collected in conference style meetings has attracted considerable interest with several large scale projects devoted to this area. In this paper we explore the use of various meeting ...
  • Transferring Impedance Control Strategies Between Heterogeneous Systems via Apprenticeship Learning 

    Howard, Matthew; Mitrovic, Djordje; Vijayakumar, Sethu (2011-01-28)
    We present a novel method for designing controllers for robots with variable impedance actuators. We take an imitation learning approach, whereby we learn impedance modulation strategies from observations of behaviour (for ...