Now showing items 599-618 of 628

  • Using decision trees within the tilt intonation model to predict f0 contours. 

    Dusterhoff, Kurt E; Black, Alan W; Taylor, Paul A (International Speech Communication Association, 1999)
    This paper presents an intonation generation system for use in a text-to-speech synthesis system. The intonation generation system uses classification trees to predict intonation event location and regression trees to ...
  • Using Dimensionality Reduction to Exploit Constraints in Reinforcement Learning 

    Bitzer, Sebastian; Howard, Matthew; Vijayakumar, Sethu (2010)
    Reinforcement learning in the high-dimensional, continuous spaces typical in robotics, remains a challenging problem. To overcome this challenge, a popular approach has been to use demonstrations to find an appropriate ...
  • Using Dutch phonological rules to model pronunciation variation in ASR 

    Wester, Mirjam; Kessens, Judith M; Strik, Helmer (University of the Saarland, 2000)
    In this paper, we describe how the performance of a continuous speech recognizer for Dutch has been improved by modeling within-word and cross-word pronunciation variation. Within-word variants were automatically generated ...
  • Using high level dialogue information for dialogue act recognition using prosodic features. 

    Wright, Helen; Poesio, Massimo; Isard, Stephen (1999)
    We look at the effect of using high level discourse knowledge in dialogue act type detection. We also look at ways this knowledge can be used for improving language modelling and intonation modelling of utterance types. ...
  • Using I-X Process Panels as Intelligent To-Do Lists for Agent Coordination in Emergency Response 

    Potter, Stephen; Tate, Austin; Wickler, Gerhard (Information Systems for Crisis Response and Management 2006 (ISCRAM2006), 2006-05)
    The aim of this paper is to describe the I-X system with its principal user interface, the I-X Process Panel, its underlying ontology, <I-N-C-A>, and how this panel can be used as an intelligent to-do list that assists ...
  • Using intonation to constrain language models in speech recognition. 

    Taylor, Paul A; King, Simon; Isard, Stephen; Wright, Helen; Kowtko, Jacqueline C (International Speech Communication Association, 1997)
    This paper describes a method for using intonation to reduce word error rate in a speech recognition system designed to recognise spontaneous dialogue speech. We use a form of dialogue analysis based on the theory of ...
  • Using Natural Language Processing to Analyze Tutorial Dialogue Corpora Across Domains and Modalities 

    Litman, Diane; Moore, Johanna D.; Dzikovska, Myroslava; Farrow, Elaine (2010-10-28)
    Our research goal is to investigate whether previous findings and methods in the area of tutorial dialogue can be generalized across dialogue corpora that differ in domain (mechanics versus electricity in physics), ...
  • Using neural networks to locate pitch accents. 

    Taylor, Paul A (International Speech Communication Association, 1995)
    This paper descirbes a technique for finding intonatioanl events, (pitch accents and boundary tones) from waveforms. The technique works in a bottom-up manner by using a recurrent neural network to perform a classification of ...
  • Using Participant Role in Multiparty Meetings as Prior Knowledge for Nonparametric Topic Modeling 

    Renals, Steve; Huang, Songfang (2008)
    In this paper we introduce our attempts to incorporate the participant role information in multiparty meetings for document modeling using the hierarchical Dirichlet process. The perplexity and automatic speech recognition ...
  • Using Prosodic Information to Constrain Language Models for Spoken Dialogue 

    Taylor, Paul A; Shimodaira, Hiroshi; Isard, Stephen; King, Simon; Kowtko, Jacqueline C (IEEE, 1996-10)
    We present work intended to improve speech recognition performance for computer dialogue by taking into account the way that dialogue context and intonational tune interact to limit the possibilities for what an utterance ...
  • Using prosodic structure to improve pitch range variation in text to speech synthesis. 

    Clark, Robert A J (International Congress of Phonetic Sciences, 1999)
    The intonation produced by current text-to-speech systems is often either flat or artificial sounding. Pitch range is one of the contributing factors which could be improved by more detailed linguistic knowledge. In ...
  • Using Real Words for Recording Diphones 

    Fitt, Susan (International Speech Communication Association, 2001)
    This paper focuses on the creation of word-lists for making diphone recordings for speech synthesis. Such lists often consist of nonsense words, which has the advantage that the phonetic environment can be constrained, and ...
  • Using statistical models to predict phrase boundaries for speech synthesis. 

    Sanders, Eric; Taylor, Paul A (International Speech Communication Association, 1995)
    This paper describes a variety of methods for inserting phrase boundaries in text. The methods work by examining the likelihood of a phrase break occurring in a sequence of three part-of-speech tags. The paper explains ...
  • Using the <I-N-C-A> Constraint Model as a Shared Representation of Intentions for Emergency Response 

    Wickler, Gerhard; Tate, Austin; Potter, Stephen (Fifth International Joint Conference on Autonomous Agents and Multiagent Systems, 2006-05-08)
    The aim of this paper is to describe the I-X system with its underlying representation: <I-N-C-A>. The latter can be seen as a description of an agent’s intentions, which can be shared and communicated amongst multiple ...
  • Utilising Spontaneous Conversational Speech in HMM-Based Speech Synthesis 

    Andersson, Sebastian; Yamagishi, Junichi; Clark, Robert (2010)
    Spontaneous conversational speech has many characteristics that are currently not well modelled in unit selection and HMM-based speech synthesis. But in order to build synthetic voices more suitable for interaction we need ...
  • Utilizing prosody for unconstrained morpheme recognition. 

    Strom, Volker; Heine, Henrik (International Speech Communication Association, 1999)
    Speech recognition systems for languages with a rich inflectional morphology (like German) suffer from the limitations of a word-based full-form lexicon. Although the morphological and acoustical knowledge about words is ...
  • Value Function Approximation on Non-Linear Manifolds for Robot Motor Control 

    Sugiyama, Masashi; Hachiya, Hirotaka; Towell, Christopher; Vijayakumar, Sethu (IEEE, 2007-04)
    The least squares approach works efficiently in value function approximation, given appropriate basis functions. Because of its smoothness, the Gaussian kernel is a popular and useful choice as a basis function. However, ...
  • Variable word rate N-grams 

    Gotoh, Yoshihiko; Renals, Steve (IEEE, 2000-06)
    The rate of occurrence of words is not uniform but varies from document to document. Despite this observation, parameters for conventional N-gram language models are usually derived using the assumption of a constant word ...
  • Ventilation and Suppression Systems in Road Tunnels: Some Issues regarding their Appropriate Use in a Fire Emergency 

    Carvel, Ricky O; Rein, Guillermo; Torero, Jose L (Tunnel Management International, 2009-03)
    Two important tunnel safety technologies are addressed. The majority of long road tunnels have ventilation systems. In the event of a fire in a tunnel, such systems will influence fire development in a number of different ...
  • Verified Planning by Deductive Synthesis in Intuitionistic Linear Logic 

    Dixon, L.; Bundy, Alan; Smaill, A. (2009)
    We describe a new formalisation in Isabelle/HOL of Intuitionistic Linear Logic and consider the support this provides for constructing plans by proving the achievability of given planning goals. The plans so found are ...